diff options
89 files changed, 1956 insertions, 659 deletions
diff --git a/Documentation/networking/ipvs-sysctl.rst b/Documentation/networking/ipvs-sysctl.rst index 95ef56d62077..387fda80f05f 100644 --- a/Documentation/networking/ipvs-sysctl.rst +++ b/Documentation/networking/ipvs-sysctl.rst @@ -37,8 +37,7 @@ conn_reuse_mode - INTEGER 0: disable any special handling on port reuse. The new connection will be delivered to the same real server that was - servicing the previous connection. This will effectively - disable expire_nodest_conn. + servicing the previous connection. bit 1: enable rescheduling of new connections when it is safe. That is, whenever expire_nodest_conn and for TCP sockets, when diff --git a/Documentation/networking/timestamping.rst b/Documentation/networking/timestamping.rst index a722eb30e014..80b13353254a 100644 --- a/Documentation/networking/timestamping.rst +++ b/Documentation/networking/timestamping.rst @@ -486,8 +486,8 @@ of packets. Drivers are free to use a more permissive configuration than the requested configuration. It is expected that drivers should only implement directly the most generic mode that can be supported. For example if the hardware can -support HWTSTAMP_FILTER_V2_EVENT, then it should generally always upscale -HWTSTAMP_FILTER_V2_L2_SYNC_MESSAGE, and so forth, as HWTSTAMP_FILTER_V2_EVENT +support HWTSTAMP_FILTER_PTP_V2_EVENT, then it should generally always upscale +HWTSTAMP_FILTER_PTP_V2_L2_SYNC, and so forth, as HWTSTAMP_FILTER_PTP_V2_EVENT is more generic (and more useful to applications). A driver which supports hardware time stamping shall update the struct diff --git a/MAINTAINERS b/MAINTAINERS index a1fb7f6307ba..360e9aa0205d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3580,13 +3580,14 @@ L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/broadcom/b44.* -BROADCOM B53 ETHERNET SWITCH DRIVER +BROADCOM B53/SF2 ETHERNET SWITCH DRIVER M: Florian Fainelli <f.fainelli@gmail.com> L: netdev@vger.kernel.org L: openwrt-devel@lists.openwrt.org (subscribers-only) S: Supported F: Documentation/devicetree/bindings/net/dsa/brcm,b53.yaml F: drivers/net/dsa/b53/* +F: drivers/net/dsa/bcm_sf2* F: include/linux/dsa/brcm.h F: include/linux/platform_data/b53.h @@ -18493,6 +18494,7 @@ F: include/uapi/linux/pkt_sched.h F: include/uapi/linux/tc_act/ F: include/uapi/linux/tc_ematch/ F: net/sched/ +F: tools/testing/selftests/tc-testing TC90522 MEDIA DRIVER M: Akihiro Tsukada <tskd08@gmail.com> diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index 43fc3087aeb3..013e9c02be71 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -1002,57 +1002,32 @@ static void ksz8_cfg_port_member(struct ksz_device *dev, int port, u8 member) data &= ~PORT_VLAN_MEMBERSHIP; data |= (member & dev->port_mask); ksz_pwrite8(dev, port, P_MIRROR_CTRL, data); - dev->ports[port].member = member; } static void ksz8_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) { struct ksz_device *dev = ds->priv; - int forward = dev->member; struct ksz_port *p; - int member = -1; u8 data; - p = &dev->ports[port]; - ksz_pread8(dev, port, P_STP_CTRL, &data); data &= ~(PORT_TX_ENABLE | PORT_RX_ENABLE | PORT_LEARN_DISABLE); switch (state) { case BR_STATE_DISABLED: data |= PORT_LEARN_DISABLE; - if (port < dev->phy_port_cnt) - member = 0; break; case BR_STATE_LISTENING: data |= (PORT_RX_ENABLE | PORT_LEARN_DISABLE); - if (port < dev->phy_port_cnt && - p->stp_state == BR_STATE_DISABLED) - member = dev->host_mask | p->vid_member; break; case BR_STATE_LEARNING: data |= PORT_RX_ENABLE; break; case BR_STATE_FORWARDING: data |= (PORT_TX_ENABLE | PORT_RX_ENABLE); - - /* This function is also used internally. */ - if (port == dev->cpu_port) - break; - - /* Port is a member of a bridge. */ - if (dev->br_member & BIT(port)) { - dev->member |= BIT(port); - member = dev->member; - } else { - member = dev->host_mask | p->vid_member; - } break; case BR_STATE_BLOCKING: data |= PORT_LEARN_DISABLE; - if (port < dev->phy_port_cnt && - p->stp_state == BR_STATE_DISABLED) - member = dev->host_mask | p->vid_member; break; default: dev_err(ds->dev, "invalid STP state: %d\n", state); @@ -1060,22 +1035,11 @@ static void ksz8_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) } ksz_pwrite8(dev, port, P_STP_CTRL, data); + + p = &dev->ports[port]; p->stp_state = state; - /* Port membership may share register with STP state. */ - if (member >= 0 && member != p->member) - ksz8_cfg_port_member(dev, port, (u8)member); - - /* Check if forwarding needs to be updated. */ - if (state != BR_STATE_FORWARDING) { - if (dev->br_member & BIT(port)) - dev->member &= ~BIT(port); - } - /* When topology has changed the function ksz_update_port_member - * should be called to modify port forwarding behavior. - */ - if (forward != dev->member) - ksz_update_port_member(dev, port); + ksz_update_port_member(dev, port); } static void ksz8_flush_dyn_mac_table(struct ksz_device *dev, int port) @@ -1341,7 +1305,7 @@ static void ksz8795_cpu_interface_select(struct ksz_device *dev, int port) static void ksz8_port_setup(struct ksz_device *dev, int port, bool cpu_port) { - struct ksz_port *p = &dev->ports[port]; + struct dsa_switch *ds = dev->ds; struct ksz8 *ksz8 = dev->priv; const u32 *masks; u8 member; @@ -1368,10 +1332,11 @@ static void ksz8_port_setup(struct ksz_device *dev, int port, bool cpu_port) if (!ksz_is_ksz88x3(dev)) ksz8795_cpu_interface_select(dev, port); - member = dev->port_mask; + member = dsa_user_ports(ds); } else { - member = dev->host_mask | p->vid_member; + member = BIT(dsa_upstream_port(ds, port)); } + ksz8_cfg_port_member(dev, port, member); } @@ -1392,20 +1357,13 @@ static void ksz8_config_cpu_port(struct dsa_switch *ds) ksz_cfg(dev, regs[S_TAIL_TAG_CTRL], masks[SW_TAIL_TAG_ENABLE], true); p = &dev->ports[dev->cpu_port]; - p->vid_member = dev->port_mask; p->on = 1; ksz8_port_setup(dev, dev->cpu_port, true); - dev->member = dev->host_mask; for (i = 0; i < dev->phy_port_cnt; i++) { p = &dev->ports[i]; - /* Initialize to non-zero so that ksz_cfg_port_member() will - * be called. - */ - p->vid_member = BIT(i); - p->member = dev->port_mask; ksz8_port_stp_state_set(ds, i, BR_STATE_DISABLED); /* Last port may be disabled. */ diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index 854e25f43fa7..353b5f981740 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -391,7 +391,6 @@ static void ksz9477_cfg_port_member(struct ksz_device *dev, int port, u8 member) { ksz_pwrite32(dev, port, REG_PORT_VLAN_MEMBERSHIP__4, member); - dev->ports[port].member = member; } static void ksz9477_port_stp_state_set(struct dsa_switch *ds, int port, @@ -400,8 +399,6 @@ static void ksz9477_port_stp_state_set(struct dsa_switch *ds, int port, struct ksz_device *dev = ds->priv; struct ksz_port *p = &dev->ports[port]; u8 data; - int member = -1; - int forward = dev->member; ksz_pread8(dev, port, P_STP_CTRL, &data); data &= ~(PORT_TX_ENABLE | PORT_RX_ENABLE | PORT_LEARN_DISABLE); @@ -409,40 +406,18 @@ static void ksz9477_port_stp_state_set(struct dsa_switch *ds, int port, switch (state) { case BR_STATE_DISABLED: data |= PORT_LEARN_DISABLE; - if (port != dev->cpu_port) - member = 0; break; case BR_STATE_LISTENING: data |= (PORT_RX_ENABLE | PORT_LEARN_DISABLE); - if (port != dev->cpu_port && - p->stp_state == BR_STATE_DISABLED) - member = dev->host_mask | p->vid_member; break; case BR_STATE_LEARNING: data |= PORT_RX_ENABLE; break; case BR_STATE_FORWARDING: data |= (PORT_TX_ENABLE | PORT_RX_ENABLE); - - /* This function is also used internally. */ - if (port == dev->cpu_port) - break; - - member = dev->host_mask | p->vid_member; - mutex_lock(&dev->dev_mutex); - - /* Port is a member of a bridge. */ - if (dev->br_member & (1 << port)) { - dev->member |= (1 << port); - member = dev->member; - } - mutex_unlock(&dev->dev_mutex); break; case BR_STATE_BLOCKING: data |= PORT_LEARN_DISABLE; - if (port != dev->cpu_port && - p->stp_state == BR_STATE_DISABLED) - member = dev->host_mask | p->vid_member; break; default: dev_err(ds->dev, "invalid STP state: %d\n", state); @@ -451,23 +426,8 @@ static void ksz9477_port_stp_state_set(struct dsa_switch *ds, int port, ksz_pwrite8(dev, port, P_STP_CTRL, data); p->stp_state = state; - mutex_lock(&dev->dev_mutex); - /* Port membership may share register with STP state. */ - if (member >= 0 && member != p->member) - ksz9477_cfg_port_member(dev, port, (u8)member); - - /* Check if forwarding needs to be updated. */ - if (state != BR_STATE_FORWARDING) { - if (dev->br_member & (1 << port)) - dev->member &= ~(1 << port); - } - /* When topology has changed the function ksz_update_port_member - * should be called to modify port forwarding behavior. - */ - if (forward != dev->member) - ksz_update_port_member(dev, port); - mutex_unlock(&dev->dev_mutex); + ksz_update_port_member(dev, port); } static void ksz9477_flush_dyn_mac_table(struct ksz_device *dev, int port) @@ -1168,10 +1128,10 @@ static void ksz9477_phy_errata_setup(struct ksz_device *dev, int port) static void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port) { - u8 data8; - u8 member; - u16 data16; struct ksz_port *p = &dev->ports[port]; + struct dsa_switch *ds = dev->ds; + u8 data8, member; + u16 data16; /* enable tag tail for host port */ if (cpu_port) @@ -1250,12 +1210,12 @@ static void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port) ksz_pwrite8(dev, port, REG_PORT_XMII_CTRL_1, data8); p->phydev.duplex = 1; } - mutex_lock(&dev->dev_mutex); + if (cpu_port) - member = dev->port_mask; + member = dsa_user_ports(ds); else - member = dev->host_mask | p->vid_member; - mutex_unlock(&dev->dev_mutex); + member = BIT(dsa_upstream_port(ds, port)); + ksz9477_cfg_port_member(dev, port, member); /* clear pending interrupts */ @@ -1276,8 +1236,6 @@ static void ksz9477_config_cpu_port(struct dsa_switch *ds) const char *prev_mode; dev->cpu_port = i; - dev->host_mask = (1 << dev->cpu_port); - dev->port_mask |= dev->host_mask; p = &dev->ports[i]; /* Read from XMII register to determine host port @@ -1312,23 +1270,15 @@ static void ksz9477_config_cpu_port(struct dsa_switch *ds) /* enable cpu port */ ksz9477_port_setup(dev, i, true); - p->vid_member = dev->port_mask; p->on = 1; } } - dev->member = dev->host_mask; - for (i = 0; i < dev->port_cnt; i++) { if (i == dev->cpu_port) continue; p = &dev->ports[i]; - /* Initialize to non-zero so that ksz_cfg_port_member() will - * be called. - */ - p->vid_member = (1 << i); - p->member = dev->port_mask; ksz9477_port_stp_state_set(ds, i, BR_STATE_DISABLED); p->on = 1; if (i < dev->phy_port_cnt) diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 7c2968a639eb..8a04302018dc 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -22,21 +22,40 @@ void ksz_update_port_member(struct ksz_device *dev, int port) { - struct ksz_port *p; + struct ksz_port *p = &dev->ports[port]; + struct dsa_switch *ds = dev->ds; + u8 port_member = 0, cpu_port; + const struct dsa_port *dp; int i; - for (i = 0; i < dev->port_cnt; i++) { - if (i == port || i == dev->cpu_port) + if (!dsa_is_user_port(ds, port)) + return; + + dp = dsa_to_port(ds, port); + cpu_port = BIT(dsa_upstream_port(ds, port)); + + for (i = 0; i < ds->num_ports; i++) { + const struct dsa_port *other_dp = dsa_to_port(ds, i); + struct ksz_port *other_p = &dev->ports[i]; + u8 val = 0; + + if (!dsa_is_user_port(ds, i)) continue; - p = &dev->ports[i]; - if (!(dev->member & (1 << i))) + if (port == i) + continue; + if (!dp->bridge_dev || dp->bridge_dev != other_dp->bridge_dev) continue; - /* Port is a member of the bridge and is forwarding. */ - if (p->stp_state == BR_STATE_FORWARDING && - p->member != dev->member) - dev->dev_ops->cfg_port_member(dev, i, dev->member); + if (other_p->stp_state == BR_STATE_FORWARDING && + p->stp_state == BR_STATE_FORWARDING) { + val |= BIT(port); + port_member |= BIT(i); + } + + dev->dev_ops->cfg_port_member(dev, i, val | cpu_port); } + + dev->dev_ops->cfg_port_member(dev, port, port_member | cpu_port); } EXPORT_SYMBOL_GPL(ksz_update_port_member); @@ -175,12 +194,6 @@ EXPORT_SYMBOL_GPL(ksz_get_ethtool_stats); int ksz_port_bridge_join(struct dsa_switch *ds, int port, struct net_device *br) { - struct ksz_device *dev = ds->priv; - - mutex_lock(&dev->dev_mutex); - dev->br_member |= (1 << port); - mutex_unlock(&dev->dev_mutex); - /* port_stp_state_set() will be called after to put the port in * appropriate state so there is no need to do anything. */ @@ -192,13 +205,6 @@ EXPORT_SYMBOL_GPL(ksz_port_bridge_join); void ksz_port_bridge_leave(struct dsa_switch *ds, int port, struct net_device *br) { - struct ksz_device *dev = ds->priv; - - mutex_lock(&dev->dev_mutex); - dev->br_member &= ~(1 << port); - dev->member &= ~(1 << port); - mutex_unlock(&dev->dev_mutex); - /* port_stp_state_set() will be called after to put the port in * forwarding state so there is no need to do anything. */ diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index 1597c63988b4..54b456bc8972 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -25,8 +25,6 @@ struct ksz_port_mib { }; struct ksz_port { - u16 member; - u16 vid_member; bool remove_tag; /* Remove Tag flag set, for ksz8795 only */ int stp_state; struct phy_device phydev; @@ -83,8 +81,6 @@ struct ksz_device { struct ksz_port *ports; struct delayed_work mib_read; unsigned long mib_read_interval; - u16 br_member; - u16 member; u16 mirror_rx; u16 mirror_tx; u32 features; /* chip specific features */ diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index a429c9750add..147ca39531a3 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -1256,8 +1256,12 @@ qca8k_setup(struct dsa_switch *ds) /* Set initial MTU for every port. * We have only have a general MTU setting. So track * every port and set the max across all port. + * Set per port MTU to 1500 as the MTU change function + * will add the overhead and if its set to 1518 then it + * will apply the overhead again and we will end up with + * MTU of 1536 instead of 1518 */ - priv->port_mtu[i] = ETH_FRAME_LEN + ETH_FCS_LEN; + priv->port_mtu[i] = ETH_DATA_LEN; } /* Special GLOBAL_FC_THRESH value are needed for ar8327 switch */ @@ -1433,6 +1437,12 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, qca8k_write(priv, QCA8K_REG_SGMII_CTRL, val); + /* From original code is reported port instability as SGMII also + * require delay set. Apply advised values here or take them from DT. + */ + if (state->interface == PHY_INTERFACE_MODE_SGMII) + qca8k_mac_config_setup_internal_delay(priv, cpu_port_index, reg); + /* For qca8327/qca8328/qca8334/qca8338 sgmii is unique and * falling edge is set writing in the PORT0 PAD reg */ @@ -1455,12 +1465,6 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, QCA8K_PORT0_PAD_SGMII_TXCLK_FALLING_EDGE, val); - /* From original code is reported port instability as SGMII also - * require delay set. Apply advised values here or take them from DT. - */ - if (state->interface == PHY_INTERFACE_MODE_SGMII) - qca8k_mac_config_setup_internal_delay(priv, cpu_port_index, reg); - break; default: dev_err(ds->dev, "xMII mode %s not supported for port %d\n", diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 24122ccda614..81b3756417ec 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -298,13 +298,14 @@ bool aq_ring_tx_clean(struct aq_ring_s *self) } } - if (unlikely(buff->is_eop)) { + if (unlikely(buff->is_eop && buff->skb)) { u64_stats_update_begin(&self->stats.tx.syncp); ++self->stats.tx.packets; self->stats.tx.bytes += buff->skb->len; u64_stats_update_end(&self->stats.tx.syncp); dev_kfree_skb_any(buff->skb); + buff->skb = NULL; } buff->pa = 0U; buff->eop_index = 0xffffU; diff --git a/drivers/net/ethernet/asix/ax88796c_spi.c b/drivers/net/ethernet/asix/ax88796c_spi.c index 94df4f96d2be..0710e716d682 100644 --- a/drivers/net/ethernet/asix/ax88796c_spi.c +++ b/drivers/net/ethernet/asix/ax88796c_spi.c @@ -34,7 +34,7 @@ int axspi_read_status(struct axspi_data *ax_spi, struct spi_status *status) /* OP */ ax_spi->cmd_buf[0] = AX_SPICMD_READ_STATUS; - ret = spi_write_then_read(ax_spi->spi, ax_spi->cmd_buf, 1, (u8 *)&status, 3); + ret = spi_write_then_read(ax_spi->spi, ax_spi->cmd_buf, 1, (u8 *)status, 3); if (ret) dev_err(&ax_spi->spi->dev, "%s() failed: ret = %d\n", __func__, ret); else diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index 64479c464b4e..ae9cca768d74 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -3196,6 +3196,7 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev, } if (adapter->registered_device_map == 0) { dev_err(&pdev->dev, "could not register any net devices\n"); + err = -EINVAL; goto err_disable_interrupts; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 67364ab63a1f..081295bff765 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -1081,7 +1081,8 @@ static void hns3_dump_page_pool_info(struct hns3_enet_ring *ring, u32 j = 0; sprintf(result[j++], "%u", index); - sprintf(result[j++], "%u", ring->page_pool->pages_state_hold_cnt); + sprintf(result[j++], "%u", + READ_ONCE(ring->page_pool->pages_state_hold_cnt)); sprintf(result[j++], "%u", atomic_read(&ring->page_pool->pages_state_release_cnt)); sprintf(result[j++], "%u", ring->page_pool->p.pool_size); @@ -1106,6 +1107,11 @@ hns3_dbg_page_pool_info(struct hnae3_handle *h, char *buf, int len) return -EFAULT; } + if (!priv->ring[h->kinfo.num_tqps].page_pool) { + dev_err(&h->pdev->dev, "page pool is not initialized\n"); + return -EFAULT; + } + for (i = 0; i < ARRAY_SIZE(page_pool_info_items); i++) result[i] = &data_str[i][0]; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index c8442b86df94..c9b4568d7a8d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -987,6 +987,7 @@ static int hns3_set_reset(struct net_device *netdev, u32 *flags) struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev); const struct hnae3_ae_ops *ops = h->ae_algo->ops; const struct hns3_reset_type_map *rst_type_map; + enum ethtool_reset_flags rst_flags; u32 i, size; if (ops->ae_dev_resetting && ops->ae_dev_resetting(h)) @@ -1006,6 +1007,7 @@ static int hns3_set_reset(struct net_device *netdev, u32 *flags) for (i = 0; i < size; i++) { if (rst_type_map[i].rst_flags == *flags) { rst_type = rst_type_map[i].rst_type; + rst_flags = rst_type_map[i].rst_flags; break; } } @@ -1021,6 +1023,8 @@ static int hns3_set_reset(struct net_device *netdev, u32 *flags) ops->reset_event(h->pdev, h); + *flags &= ~rst_flags; + return 0; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 25c419d40066..41afaeea881b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -703,9 +703,9 @@ static int hclgevf_set_rss_tc_mode(struct hclgevf_dev *hdev, u16 rss_size) roundup_size = ilog2(roundup_size); for (i = 0; i < HCLGEVF_MAX_TC_NUM; i++) { - tc_valid[i] = !!(hdev->hw_tc_map & BIT(i)); + tc_valid[i] = 1; tc_size[i] = roundup_size; - tc_offset[i] = rss_size * i; + tc_offset[i] = (hdev->hw_tc_map & BIT(i)) ? rss_size * i : 0; } hclgevf_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_RSS_TC_MODE, false); diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 75635bd57cf6..3789269ce741 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -305,6 +305,7 @@ struct iavf_adapter { #define IAVF_FLAG_AQ_DEL_FDIR_FILTER BIT(26) #define IAVF_FLAG_AQ_ADD_ADV_RSS_CFG BIT(27) #define IAVF_FLAG_AQ_DEL_ADV_RSS_CFG BIT(28) +#define IAVF_FLAG_AQ_REQUEST_STATS BIT(29) /* OS defined structs */ struct net_device *netdev; @@ -444,6 +445,7 @@ int iavf_up(struct iavf_adapter *adapter); void iavf_down(struct iavf_adapter *adapter); int iavf_process_config(struct iavf_adapter *adapter); void iavf_schedule_reset(struct iavf_adapter *adapter); +void iavf_schedule_request_stats(struct iavf_adapter *adapter); void iavf_reset(struct iavf_adapter *adapter); void iavf_set_ethtool_ops(struct net_device *netdev); void iavf_update_stats(struct iavf_adapter *adapter); @@ -501,4 +503,5 @@ void iavf_add_adv_rss_cfg(struct iavf_adapter *adapter); void iavf_del_adv_rss_cfg(struct iavf_adapter *adapter); struct iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter, const u8 *macaddr); +int iavf_lock_timeout(struct mutex *lock, unsigned int msecs); #endif /* _IAVF_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 144a77679359..0cecaff38d04 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -354,6 +354,9 @@ static void iavf_get_ethtool_stats(struct net_device *netdev, struct iavf_adapter *adapter = netdev_priv(netdev); unsigned int i; + /* Explicitly request stats refresh */ + iavf_schedule_request_stats(adapter); + iavf_add_ethtool_stats(&data, adapter, iavf_gstrings_stats); rcu_read_lock(); @@ -723,12 +726,31 @@ static int iavf_get_per_queue_coalesce(struct net_device *netdev, u32 queue, * * Change the ITR settings for a specific queue. **/ -static void iavf_set_itr_per_queue(struct iavf_adapter *adapter, - struct ethtool_coalesce *ec, int queue) +static int iavf_set_itr_per_queue(struct iavf_adapter *adapter, + struct ethtool_coalesce *ec, int queue) { struct iavf_ring *rx_ring = &adapter->rx_rings[queue]; struct iavf_ring *tx_ring = &adapter->tx_rings[queue]; struct iavf_q_vector *q_vector; + u16 itr_setting; + + itr_setting = rx_ring->itr_setting & ~IAVF_ITR_DYNAMIC; + + if (ec->rx_coalesce_usecs != itr_setting && + ec->use_adaptive_rx_coalesce) { + netif_info(adapter, drv, adapter->netdev, + "Rx interrupt throttling cannot be changed if adaptive-rx is enabled\n"); + return -EINVAL; + } + + itr_setting = tx_ring->itr_setting & ~IAVF_ITR_DYNAMIC; + + if (ec->tx_coalesce_usecs != itr_setting && + ec->use_adaptive_tx_coalesce) { + netif_info(adapter, drv, adapter->netdev, + "Tx interrupt throttling cannot be changed if adaptive-tx is enabled\n"); + return -EINVAL; + } rx_ring->itr_setting = ITR_REG_ALIGN(ec->rx_coalesce_usecs); tx_ring->itr_setting = ITR_REG_ALIGN(ec->tx_coalesce_usecs); @@ -751,6 +773,7 @@ static void iavf_set_itr_per_queue(struct iavf_adapter *adapter, * the Tx and Rx ITR values based on the values we have entered * into the q_vector, no need to write the values now. */ + return 0; } /** @@ -792,9 +815,11 @@ static int __iavf_set_coalesce(struct net_device *netdev, */ if (queue < 0) { for (i = 0; i < adapter->num_active_queues; i++) - iavf_set_itr_per_queue(adapter, ec, i); + if (iavf_set_itr_per_queue(adapter, ec, i)) + return -EINVAL; } else if (queue < adapter->num_active_queues) { - iavf_set_itr_per_queue(adapter, ec, queue); + if (iavf_set_itr_per_queue(adapter, ec, queue)) + return -EINVAL; } else { netif_info(adapter, drv, netdev, "Invalid queue value, queue range is 0 - %d\n", adapter->num_active_queues - 1); diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 336e6bf95e48..14934a7a13ef 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -147,7 +147,7 @@ enum iavf_status iavf_free_virt_mem_d(struct iavf_hw *hw, * * Returns 0 on success, negative on failure **/ -static int iavf_lock_timeout(struct mutex *lock, unsigned int msecs) +int iavf_lock_timeout(struct mutex *lock, unsigned int msecs) { unsigned int wait, delay = 10; @@ -175,6 +175,19 @@ void iavf_schedule_reset(struct iavf_adapter *adapter) } /** + * iavf_schedule_request_stats - Set the flags and schedule statistics request + * @adapter: board private structure + * + * Sets IAVF_FLAG_AQ_REQUEST_STATS flag so iavf_watchdog_task() will explicitly + * request and refresh ethtool stats + **/ +void iavf_schedule_request_stats(struct iavf_adapter *adapter) +{ + adapter->aq_required |= IAVF_FLAG_AQ_REQUEST_STATS; + mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0); +} + +/** * iavf_tx_timeout - Respond to a Tx Hang * @netdev: network interface device structure * @txqueue: queue number that is timing out @@ -704,13 +717,11 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, u16 vlan) **/ static void iavf_restore_filters(struct iavf_adapter *adapter) { - /* re-add all VLAN filters */ - if (VLAN_ALLOWED(adapter)) { - u16 vid; + u16 vid; - for_each_set_bit(vid, adapter->vsi.active_vlans, VLAN_N_VID) - iavf_add_vlan(adapter, vid); - } + /* re-add all VLAN filters */ + for_each_set_bit(vid, adapter->vsi.active_vlans, VLAN_N_VID) + iavf_add_vlan(adapter, vid); } /** @@ -745,9 +756,6 @@ static int iavf_vlan_rx_kill_vid(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); - if (!VLAN_ALLOWED(adapter)) - return -EIO; - iavf_del_vlan(adapter, vid); clear_bit(vid, adapter->vsi.active_vlans); @@ -1709,6 +1717,11 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter) iavf_del_adv_rss_cfg(adapter); return 0; } + if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_STATS) { + iavf_request_stats(adapter); + return 0; + } + return -EAGAIN; } @@ -2173,7 +2186,6 @@ static void iavf_reset_task(struct work_struct *work) struct net_device *netdev = adapter->netdev; struct iavf_hw *hw = &adapter->hw; struct iavf_mac_filter *f, *ftmp; - struct iavf_vlan_filter *vlf; struct iavf_cloud_filter *cf; u32 reg_val; int i = 0, err; @@ -2254,6 +2266,7 @@ continue_reset: (adapter->state == __IAVF_RESETTING)); if (running) { + netdev->flags &= ~IFF_UP; netif_carrier_off(netdev); netif_tx_stop_all_queues(netdev); adapter->link_up = false; @@ -2313,11 +2326,6 @@ continue_reset: list_for_each_entry(f, &adapter->mac_filter_list, list) { f->add = true; } - /* re-add all VLAN filters */ - list_for_each_entry(vlf, &adapter->vlan_filter_list, list) { - vlf->add = true; - } - spin_unlock_bh(&adapter->mac_vlan_list_lock); /* check if TCs are running and re-add all cloud filters */ @@ -2331,7 +2339,6 @@ continue_reset: spin_unlock_bh(&adapter->cloud_filter_list_lock); adapter->aq_required |= IAVF_FLAG_AQ_ADD_MAC_FILTER; - adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; adapter->aq_required |= IAVF_FLAG_AQ_ADD_CLOUD_FILTER; iavf_misc_irq_enable(adapter); @@ -2365,7 +2372,7 @@ continue_reset: * to __IAVF_RUNNING */ iavf_up_complete(adapter); - + netdev->flags |= IFF_UP; iavf_irq_enable(adapter, true); } else { iavf_change_state(adapter, __IAVF_DOWN); @@ -2378,8 +2385,10 @@ continue_reset: reset_err: mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); - if (running) + if (running) { iavf_change_state(adapter, __IAVF_RUNNING); + netdev->flags |= IFF_UP; + } dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); iavf_close(netdev); } @@ -3441,11 +3450,16 @@ static int iavf_set_features(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); - /* Don't allow changing VLAN_RX flag when adapter is not capable - * of VLAN offload + /* Don't allow enabling VLAN features when adapter is not capable + * of VLAN offload/filtering */ if (!VLAN_ALLOWED(adapter)) { - if ((netdev->features ^ features) & NETIF_F_HW_VLAN_CTAG_RX) + netdev->hw_features &= ~(NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_FILTER); + if (features & (NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_FILTER)) return -EINVAL; } else if ((netdev->features ^ features) & NETIF_F_HW_VLAN_CTAG_RX) { if (features & NETIF_F_HW_VLAN_CTAG_RX) diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 8c3f0f77cb57..d60bf7c21200 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -607,7 +607,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) if (f->add) count++; } - if (!count) { + if (!count || !VLAN_ALLOWED(adapter)) { adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_VLAN_FILTER; spin_unlock_bh(&adapter->mac_vlan_list_lock); return; @@ -673,9 +673,19 @@ void iavf_del_vlans(struct iavf_adapter *adapter) spin_lock_bh(&adapter->mac_vlan_list_lock); - list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->remove) + list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { + /* since VLAN capabilities are not allowed, we dont want to send + * a VLAN delete request because it will most likely fail and + * create unnecessary errors/noise, so just free the VLAN + * filters marked for removal to enable bailing out before + * sending a virtchnl message + */ + if (f->remove && !VLAN_ALLOWED(adapter)) { + list_del(&f->list); + kfree(f); + } else if (f->remove) { count++; + } } if (!count) { adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_VLAN_FILTER; @@ -784,6 +794,8 @@ void iavf_request_stats(struct iavf_adapter *adapter) /* no error message, this isn't crucial */ return; } + + adapter->aq_required &= ~IAVF_FLAG_AQ_REQUEST_STATS; adapter->current_op = VIRTCHNL_OP_GET_STATS; vqs.vsi_id = adapter->vsi_res->vsi_id; /* queue maps are ignored for this message - only the vsi is used */ @@ -1722,8 +1734,37 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, } spin_lock_bh(&adapter->mac_vlan_list_lock); iavf_add_filter(adapter, adapter->hw.mac.addr); + + if (VLAN_ALLOWED(adapter)) { + if (!list_empty(&adapter->vlan_filter_list)) { + struct iavf_vlan_filter *vlf; + + /* re-add all VLAN filters over virtchnl */ + list_for_each_entry(vlf, + &adapter->vlan_filter_list, + list) + vlf->add = true; + + adapter->aq_required |= + IAVF_FLAG_AQ_ADD_VLAN_FILTER; + } + } + spin_unlock_bh(&adapter->mac_vlan_list_lock); iavf_process_config(adapter); + + /* unlock crit_lock before acquiring rtnl_lock as other + * processes holding rtnl_lock could be waiting for the same + * crit_lock + */ + mutex_unlock(&adapter->crit_lock); + rtnl_lock(); + netdev_update_features(adapter->netdev); + rtnl_unlock(); + if (iavf_lock_timeout(&adapter->crit_lock, 10000)) + dev_warn(&adapter->pdev->dev, "failed to acquire crit_lock in %s\n", + __FUNCTION__); + } break; case VIRTCHNL_OP_ENABLE_QUEUES: diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 40562600a8cf..09a3297cd63c 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -89,8 +89,13 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi) if (!vsi->rx_rings) goto err_rings; - /* XDP will have vsi->alloc_txq Tx queues as well, so double the size */ - vsi->txq_map = devm_kcalloc(dev, (2 * vsi->alloc_txq), + /* txq_map needs to have enough space to track both Tx (stack) rings + * and XDP rings; at this point vsi->num_xdp_txq might not be set, + * so use num_possible_cpus() as we want to always provide XDP ring + * per CPU, regardless of queue count settings from user that might + * have come from ethtool's set_channels() callback; + */ + vsi->txq_map = devm_kcalloc(dev, (vsi->alloc_txq + num_possible_cpus()), sizeof(*vsi->txq_map), GFP_KERNEL); if (!vsi->txq_map) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index f099797f35e3..4d1fc48c9744 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2609,7 +2609,18 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) ice_stat_str(status)); goto clear_xdp_rings; } - ice_vsi_assign_bpf_prog(vsi, prog); + + /* assign the prog only when it's not already present on VSI; + * this flow is a subject of both ethtool -L and ndo_bpf flows; + * VSI rebuild that happens under ethtool -L can expose us to + * the bpf_prog refcount issues as we would be swapping same + * bpf_prog pointers from vsi->xdp_prog and calling bpf_prog_put + * on it as it would be treated as an 'old_prog'; for ndo_bpf + * this is not harmful as dev_xdp_install bumps the refcount + * before calling the op exposed by the driver; + */ + if (!ice_is_xdp_ena_vsi(vsi)) + ice_vsi_assign_bpf_prog(vsi, prog); return 0; clear_xdp_rings: @@ -2785,6 +2796,11 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, if (xdp_ring_err) NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx resources failed"); } else { + /* safe to call even when prog == vsi->xdp_prog as + * dev_xdp_install in net/core/dev.c incremented prog's + * refcount so corresponding bpf_prog_put won't cause + * underflow + */ ice_vsi_assign_bpf_prog(vsi, prog); } diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 836be0d3b291..fd54d3ef890b 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -8026,7 +8026,7 @@ static int igb_poll(struct napi_struct *napi, int budget) if (likely(napi_complete_done(napi, work_done))) igb_ring_irq_enable(q_vector); - return min(work_done, budget - 1); + return work_done; } /** diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 2b18d89d9756..ce486e16489c 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -5017,11 +5017,13 @@ static int mvpp2_change_mtu(struct net_device *dev, int mtu) mtu = ALIGN(MVPP2_RX_PKT_SIZE(mtu), 8); } + if (port->xdp_prog && mtu > MVPP2_MAX_RX_BUF_SIZE) { + netdev_err(dev, "Illegal MTU value %d (> %d) for XDP mode\n", + mtu, (int)MVPP2_MAX_RX_BUF_SIZE); + return -EINVAL; + } + if (MVPP2_RX_PKT_SIZE(mtu) > MVPP2_BM_LONG_PKT_SIZE) { - if (port->xdp_prog) { - netdev_err(dev, "Jumbo frames are not supported with XDP\n"); - return -EINVAL; - } if (priv->percpu_pools) { netdev_warn(dev, "mtu %d too high, switching to shared buffers", mtu); mvpp2_bm_switch_buffers(priv, false); @@ -5307,8 +5309,8 @@ static int mvpp2_xdp_setup(struct mvpp2_port *port, struct netdev_bpf *bpf) bool running = netif_running(port->dev); bool reset = !prog != !port->xdp_prog; - if (port->dev->mtu > ETH_DATA_LEN) { - NL_SET_ERR_MSG_MOD(bpf->extack, "XDP is not supported with jumbo frames enabled"); + if (port->dev->mtu > MVPP2_MAX_RX_BUF_SIZE) { + NL_SET_ERR_MSG_MOD(bpf->extack, "MTU too large for XDP"); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c index 3ce6ccd0f539..b4599fe4ca8d 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c @@ -497,8 +497,8 @@ int prestera_bridge_port_join(struct net_device *br_dev, br_port = prestera_bridge_port_add(bridge, port->dev); if (IS_ERR(br_port)) { - err = PTR_ERR(br_port); - goto err_brport_create; + prestera_bridge_put(bridge); + return PTR_ERR(br_port); } err = switchdev_bridge_port_offload(br_port->dev, port->dev, NULL, @@ -519,8 +519,6 @@ err_port_join: switchdev_bridge_port_unoffload(br_port->dev, NULL, NULL, NULL); err_switchdev_offload: prestera_bridge_port_put(br_port); -err_brport_create: - prestera_bridge_put(bridge); return err; } @@ -1124,7 +1122,7 @@ static int prestera_switchdev_blk_event(struct notifier_block *unused, prestera_port_obj_attr_set); break; default: - err = -EOPNOTSUPP; + return NOTIFY_DONE; } return notifier_from_errno(err); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 5925db386b1b..03e5bad4e405 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -2153,7 +2153,7 @@ static void mlxsw_sp_pude_event_func(const struct mlxsw_reg_info *reg, max_ports = mlxsw_core_max_ports(mlxsw_sp->core); local_port = mlxsw_reg_pude_local_port_get(pude_pl); - if (WARN_ON_ONCE(local_port >= max_ports)) + if (WARN_ON_ONCE(!local_port || local_port >= max_ports)) return; mlxsw_sp_port = mlxsw_sp->ports[local_port]; if (!mlxsw_sp_port) @@ -3290,10 +3290,10 @@ mlxsw_sp_resources_rif_mac_profile_register(struct mlxsw_core *mlxsw_core) u8 max_rif_mac_profiles; if (!MLXSW_CORE_RES_VALID(mlxsw_core, MAX_RIF_MAC_PROFILES)) - return -EIO; - - max_rif_mac_profiles = MLXSW_CORE_RES_GET(mlxsw_core, - MAX_RIF_MAC_PROFILES); + max_rif_mac_profiles = 1; + else + max_rif_mac_profiles = MLXSW_CORE_RES_GET(mlxsw_core, + MAX_RIF_MAC_PROFILES); devlink_resource_size_params_init(&size_params, max_rif_mac_profiles, max_rif_mac_profiles, 1, DEVLINK_RESOURCE_UNIT_ENTRY); diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 4fc97823bc84..7d7647481f70 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -914,8 +914,7 @@ static int lan743x_phy_reset(struct lan743x_adapter *adapter) } static void lan743x_phy_update_flowcontrol(struct lan743x_adapter *adapter, - u8 duplex, u16 local_adv, - u16 remote_adv) + u16 local_adv, u16 remote_adv) { struct lan743x_phy *phy = &adapter->phy; u8 cap; @@ -943,7 +942,6 @@ static void lan743x_phy_link_status_change(struct net_device *netdev) phy_print_status(phydev); if (phydev->state == PHY_RUNNING) { - struct ethtool_link_ksettings ksettings; int remote_advertisement = 0; int local_advertisement = 0; @@ -980,18 +978,14 @@ static void lan743x_phy_link_status_change(struct net_device *netdev) } lan743x_csr_write(adapter, MAC_CR, data); - memset(&ksettings, 0, sizeof(ksettings)); - phy_ethtool_get_link_ksettings(netdev, &ksettings); local_advertisement = linkmode_adv_to_mii_adv_t(phydev->advertising); remote_advertisement = linkmode_adv_to_mii_adv_t(phydev->lp_advertising); - lan743x_phy_update_flowcontrol(adapter, - ksettings.base.duplex, - local_advertisement, + lan743x_phy_update_flowcontrol(adapter, local_advertisement, remote_advertisement); - lan743x_ptp_update_latency(adapter, ksettings.base.speed); + lan743x_ptp_update_latency(adapter, phydev->speed); } } diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index e6c18b598d5c..409cde1e59c6 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1278,6 +1278,225 @@ int ocelot_fdb_dump(struct ocelot *ocelot, int port, } EXPORT_SYMBOL(ocelot_fdb_dump); +static void ocelot_populate_l2_ptp_trap_key(struct ocelot_vcap_filter *trap) +{ + trap->key_type = OCELOT_VCAP_KEY_ETYPE; + *(__be16 *)trap->key.etype.etype.value = htons(ETH_P_1588); + *(__be16 *)trap->key.etype.etype.mask = htons(0xffff); +} + +static void +ocelot_populate_ipv4_ptp_event_trap_key(struct ocelot_vcap_filter *trap) +{ + trap->key_type = OCELOT_VCAP_KEY_IPV4; + trap->key.ipv4.dport.value = PTP_EV_PORT; + trap->key.ipv4.dport.mask = 0xffff; +} + +static void +ocelot_populate_ipv6_ptp_event_trap_key(struct ocelot_vcap_filter *trap) +{ + trap->key_type = OCELOT_VCAP_KEY_IPV6; + trap->key.ipv6.dport.value = PTP_EV_PORT; + trap->key.ipv6.dport.mask = 0xffff; +} + +static void +ocelot_populate_ipv4_ptp_general_trap_key(struct ocelot_vcap_filter *trap) +{ + trap->key_type = OCELOT_VCAP_KEY_IPV4; + trap->key.ipv4.dport.value = PTP_GEN_PORT; + trap->key.ipv4.dport.mask = 0xffff; +} + +static void +ocelot_populate_ipv6_ptp_general_trap_key(struct ocelot_vcap_filter *trap) +{ + trap->key_type = OCELOT_VCAP_KEY_IPV6; + trap->key.ipv6.dport.value = PTP_GEN_PORT; + trap->key.ipv6.dport.mask = 0xffff; +} + +static int ocelot_trap_add(struct ocelot *ocelot, int port, + unsigned long cookie, + void (*populate)(struct ocelot_vcap_filter *f)) +{ + struct ocelot_vcap_block *block_vcap_is2; + struct ocelot_vcap_filter *trap; + bool new = false; + int err; + + block_vcap_is2 = &ocelot->block[VCAP_IS2]; + + trap = ocelot_vcap_block_find_filter_by_id(block_vcap_is2, cookie, + false); + if (!trap) { + trap = kzalloc(sizeof(*trap), GFP_KERNEL); + if (!trap) + return -ENOMEM; + + populate(trap); + trap->prio = 1; + trap->id.cookie = cookie; + trap->id.tc_offload = false; + trap->block_id = VCAP_IS2; + trap->type = OCELOT_VCAP_FILTER_OFFLOAD; + trap->lookup = 0; + trap->action.cpu_copy_ena = true; + trap->action.mask_mode = OCELOT_MASK_MODE_PERMIT_DENY; + trap->action.port_mask = 0; + new = true; + } + + trap->ingress_port_mask |= BIT(port); + + if (new) + err = ocelot_vcap_filter_add(ocelot, trap, NULL); + else + err = ocelot_vcap_filter_replace(ocelot, trap); + if (err) { + trap->ingress_port_mask &= ~BIT(port); + if (!trap->ingress_port_mask) + kfree(trap); + return err; + } + + return 0; +} + +static int ocelot_trap_del(struct ocelot *ocelot, int port, + unsigned long cookie) +{ + struct ocelot_vcap_block *block_vcap_is2; + struct ocelot_vcap_filter *trap; + + block_vcap_is2 = &ocelot->block[VCAP_IS2]; + + trap = ocelot_vcap_block_find_filter_by_id(block_vcap_is2, cookie, + false); + if (!trap) + return 0; + + trap->ingress_port_mask &= ~BIT(port); + if (!trap->ingress_port_mask) + return ocelot_vcap_filter_del(ocelot, trap); + + return ocelot_vcap_filter_replace(ocelot, trap); +} + +static int ocelot_l2_ptp_trap_add(struct ocelot *ocelot, int port) +{ + unsigned long l2_cookie = ocelot->num_phys_ports + 1; + + return ocelot_trap_add(ocelot, port, l2_cookie, + ocelot_populate_l2_ptp_trap_key); +} + +static int ocelot_l2_ptp_trap_del(struct ocelot *ocelot, int port) +{ + unsigned long l2_cookie = ocelot->num_phys_ports + 1; + + return ocelot_trap_del(ocelot, port, l2_cookie); +} + +static int ocelot_ipv4_ptp_trap_add(struct ocelot *ocelot, int port) +{ + unsigned long ipv4_gen_cookie = ocelot->num_phys_ports + 2; + unsigned long ipv4_ev_cookie = ocelot->num_phys_ports + 3; + int err; + + err = ocelot_trap_add(ocelot, port, ipv4_ev_cookie, + ocelot_populate_ipv4_ptp_event_trap_key); + if (err) + return err; + + err = ocelot_trap_add(ocelot, port, ipv4_gen_cookie, + ocelot_populate_ipv4_ptp_general_trap_key); + if (err) + ocelot_trap_del(ocelot, port, ipv4_ev_cookie); + + return err; +} + +static int ocelot_ipv4_ptp_trap_del(struct ocelot *ocelot, int port) +{ + unsigned long ipv4_gen_cookie = ocelot->num_phys_ports + 2; + unsigned long ipv4_ev_cookie = ocelot->num_phys_ports + 3; + int err; + + err = ocelot_trap_del(ocelot, port, ipv4_ev_cookie); + err |= ocelot_trap_del(ocelot, port, ipv4_gen_cookie); + return err; +} + +static int ocelot_ipv6_ptp_trap_add(struct ocelot *ocelot, int port) +{ + unsigned long ipv6_gen_cookie = ocelot->num_phys_ports + 4; + unsigned long ipv6_ev_cookie = ocelot->num_phys_ports + 5; + int err; + + err = ocelot_trap_add(ocelot, port, ipv6_ev_cookie, + ocelot_populate_ipv6_ptp_event_trap_key); + if (err) + return err; + + err = ocelot_trap_add(ocelot, port, ipv6_gen_cookie, + ocelot_populate_ipv6_ptp_general_trap_key); + if (err) + ocelot_trap_del(ocelot, port, ipv6_ev_cookie); + + return err; +} + +static int ocelot_ipv6_ptp_trap_del(struct ocelot *ocelot, int port) +{ + unsigned long ipv6_gen_cookie = ocelot->num_phys_ports + 4; + unsigned long ipv6_ev_cookie = ocelot->num_phys_ports + 5; + int err; + + err = ocelot_trap_del(ocelot, port, ipv6_ev_cookie); + err |= ocelot_trap_del(ocelot, port, ipv6_gen_cookie); + return err; +} + +static int ocelot_setup_ptp_traps(struct ocelot *ocelot, int port, + bool l2, bool l4) +{ + int err; + + if (l2) + err = ocelot_l2_ptp_trap_add(ocelot, port); + else + err = ocelot_l2_ptp_trap_del(ocelot, port); + if (err) + return err; + + if (l4) { + err = ocelot_ipv4_ptp_trap_add(ocelot, port); + if (err) + goto err_ipv4; + + err = ocelot_ipv6_ptp_trap_add(ocelot, port); + if (err) + goto err_ipv6; + } else { + err = ocelot_ipv4_ptp_trap_del(ocelot, port); + + err |= ocelot_ipv6_ptp_trap_del(ocelot, port); + } + if (err) + return err; + + return 0; + +err_ipv6: + ocelot_ipv4_ptp_trap_del(ocelot, port); +err_ipv4: + if (l2) + ocelot_l2_ptp_trap_del(ocelot, port); + return err; +} + int ocelot_hwstamp_get(struct ocelot *ocelot, int port, struct ifreq *ifr) { return copy_to_user(ifr->ifr_data, &ocelot->hwtstamp_config, @@ -1288,7 +1507,9 @@ EXPORT_SYMBOL(ocelot_hwstamp_get); int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr) { struct ocelot_port *ocelot_port = ocelot->ports[port]; + bool l2 = false, l4 = false; struct hwtstamp_config cfg; + int err; if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; @@ -1320,28 +1541,40 @@ int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr) switch (cfg.rx_filter) { case HWTSTAMP_FILTER_NONE: break; - case HWTSTAMP_FILTER_ALL: - case HWTSTAMP_FILTER_SOME: - case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: - case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: - case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: - case HWTSTAMP_FILTER_NTP_ALL: case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + l4 = true; + break; case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + l2 = true; + break; case HWTSTAMP_FILTER_PTP_V2_EVENT: case HWTSTAMP_FILTER_PTP_V2_SYNC: case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: - cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + l2 = true; + l4 = true; break; default: mutex_unlock(&ocelot->ptp_lock); return -ERANGE; } + err = ocelot_setup_ptp_traps(ocelot, port, l2, l4); + if (err) + return err; + + if (l2 && l4) + cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + else if (l2) + cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT; + else if (l4) + cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT; + else + cfg.rx_filter = HWTSTAMP_FILTER_NONE; + /* Commit back the result & save it */ memcpy(&ocelot->hwtstamp_config, &cfg, sizeof(cfg)); mutex_unlock(&ocelot->ptp_lock); @@ -1444,7 +1677,10 @@ int ocelot_get_ts_info(struct ocelot *ocelot, int port, SOF_TIMESTAMPING_RAW_HARDWARE; info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON) | BIT(HWTSTAMP_TX_ONESTEP_SYNC); - info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | BIT(HWTSTAMP_FILTER_ALL); + info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | + BIT(HWTSTAMP_FILTER_PTP_V2_EVENT) | + BIT(HWTSTAMP_FILTER_PTP_V2_L2_EVENT) | + BIT(HWTSTAMP_FILTER_PTP_V2_L4_EVENT); return 0; } diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.c b/drivers/net/ethernet/mscc/ocelot_vcap.c index 99d7376a70a7..337cd08b1a54 100644 --- a/drivers/net/ethernet/mscc/ocelot_vcap.c +++ b/drivers/net/ethernet/mscc/ocelot_vcap.c @@ -1217,6 +1217,22 @@ int ocelot_vcap_filter_del(struct ocelot *ocelot, } EXPORT_SYMBOL(ocelot_vcap_filter_del); +int ocelot_vcap_filter_replace(struct ocelot *ocelot, + struct ocelot_vcap_filter *filter) +{ + struct ocelot_vcap_block *block = &ocelot->block[filter->block_id]; + int index; + + index = ocelot_vcap_block_get_filter_index(block, filter); + if (index < 0) + return index; + + vcap_entry_set(ocelot, index, filter); + + return 0; +} +EXPORT_SYMBOL(ocelot_vcap_filter_replace); + int ocelot_vcap_filter_stats_update(struct ocelot *ocelot, struct ocelot_vcap_filter *filter) { diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index df203738511b..0b1865e9f0b5 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -565,7 +565,6 @@ struct nfp_net_dp { * @exn_name: Name for Exception interrupt * @shared_handler: Handler for shared interrupts * @shared_name: Name for shared interrupt - * @me_freq_mhz: ME clock_freq (MHz) * @reconfig_lock: Protects @reconfig_posted, @reconfig_timer_active, * @reconfig_sync_present and HW reconfiguration request * regs/machinery from async requests (sync must take @@ -650,8 +649,6 @@ struct nfp_net { irq_handler_t shared_handler; char shared_name[IFNAMSIZ + 8]; - u32 me_freq_mhz; - bool link_up; spinlock_t link_status_lock; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index 1de076f55740..cf7882933993 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -1344,7 +1344,7 @@ static int nfp_net_set_coalesce(struct net_device *netdev, * ME timestamp ticks. There are 16 ME clock cycles for each timestamp * count. */ - factor = nn->me_freq_mhz / 16; + factor = nn->tlv_caps.me_freq_mhz / 16; /* Each pair of (usecs, max_frames) fields specifies that interrupts * should be coalesced until diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c index cfeb7620ae20..07a00dd9cfe0 100644 --- a/drivers/net/ethernet/ni/nixge.c +++ b/drivers/net/ethernet/ni/nixge.c @@ -1209,7 +1209,7 @@ static void *nixge_get_nvmem_address(struct device *dev) cell = nvmem_cell_get(dev, "address"); if (IS_ERR(cell)) - return NULL; + return cell; mac = nvmem_cell_read(cell, &cell_size); nvmem_cell_put(cell); @@ -1282,7 +1282,7 @@ static int nixge_probe(struct platform_device *pdev) ndev->max_mtu = NIXGE_JUMBO_MTU; mac_addr = nixge_get_nvmem_address(&pdev->dev); - if (mac_addr && is_valid_ether_addr(mac_addr)) { + if (!IS_ERR(mac_addr) && is_valid_ether_addr(mac_addr)) { eth_hw_addr_set(ndev, mac_addr); kfree(mac_addr); } else { diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c index a97f691839e0..6958adeca86d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.c +++ b/drivers/net/ethernet/qlogic/qed/qed_int.c @@ -1045,7 +1045,7 @@ static int qed_int_deassertion(struct qed_hwfn *p_hwfn, if (!parities) continue; - for (j = 0, bit_idx = 0; bit_idx < 32; j++) { + for (j = 0, bit_idx = 0; bit_idx < 32 && j < 32; j++) { struct aeu_invert_reg_bit *p_bit = &p_aeu->bits[j]; if (qed_int_is_parity_flag(p_hwfn, p_bit) && @@ -1083,7 +1083,7 @@ static int qed_int_deassertion(struct qed_hwfn *p_hwfn, * to current group, making them responsible for the * previous assertion. */ - for (j = 0, bit_idx = 0; bit_idx < 32; j++) { + for (j = 0, bit_idx = 0; bit_idx < 32 && j < 32; j++) { long unsigned int bitmask; u8 bit, bit_len; @@ -1382,7 +1382,7 @@ static void qed_int_sb_attn_init(struct qed_hwfn *p_hwfn, memset(sb_info->parity_mask, 0, sizeof(u32) * NUM_ATTN_REGS); for (i = 0; i < NUM_ATTN_REGS; i++) { /* j is array index, k is bit index */ - for (j = 0, k = 0; k < 32; j++) { + for (j = 0, k = 0; k < 32 && j < 32; j++) { struct aeu_invert_reg_bit *p_aeu; p_aeu = &aeu_descs[i].bits[j]; diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index bbe21db20417..86c44bc5f73f 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -5217,8 +5217,8 @@ static int rtl_get_ether_clk(struct rtl8169_private *tp) static void rtl_init_mac_address(struct rtl8169_private *tp) { + u8 mac_addr[ETH_ALEN] __aligned(2) = {}; struct net_device *dev = tp->dev; - u8 mac_addr[ETH_ALEN]; int rc; rc = eth_platform_get_mac_address(tp_to_dev(tp), mac_addr); @@ -5233,7 +5233,8 @@ static void rtl_init_mac_address(struct rtl8169_private *tp) if (is_valid_ether_addr(mac_addr)) goto done; - eth_hw_addr_random(dev); + eth_random_addr(mac_addr); + dev->addr_assign_type = NET_ADDR_RANDOM; dev_warn(tp_to_dev(tp), "can't read MAC address, setting random one\n"); done: eth_hw_addr_set(dev, mac_addr); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 43eead726886..5f129733aabd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -314,6 +314,7 @@ int stmmac_mdio_reset(struct mii_bus *mii); int stmmac_xpcs_setup(struct mii_bus *mii); void stmmac_set_ethtool_ops(struct net_device *netdev); +int stmmac_init_tstamp_counter(struct stmmac_priv *priv, u32 systime_flags); void stmmac_ptp_register(struct stmmac_priv *priv); void stmmac_ptp_unregister(struct stmmac_priv *priv); int stmmac_open(struct net_device *dev); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 2eb284576336..748195697e5a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -50,6 +50,13 @@ #include "dwxgmac2.h" #include "hwif.h" +/* As long as the interface is active, we keep the timestamping counter enabled + * with fine resolution and binary rollover. This avoid non-monotonic behavior + * (clock jumps) when changing timestamping settings at runtime. + */ +#define STMMAC_HWTS_ACTIVE (PTP_TCR_TSENA | PTP_TCR_TSCFUPDT | \ + PTP_TCR_TSCTRLSSR) + #define STMMAC_ALIGN(x) ALIGN(ALIGN(x, SMP_CACHE_BYTES), 16) #define TSO_MAX_BUFF_SIZE (SZ_16K - 1) @@ -613,8 +620,6 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) { struct stmmac_priv *priv = netdev_priv(dev); struct hwtstamp_config config; - struct timespec64 now; - u64 temp = 0; u32 ptp_v2 = 0; u32 tstamp_all = 0; u32 ptp_over_ipv4_udp = 0; @@ -623,11 +628,6 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) u32 snap_type_sel = 0; u32 ts_master_en = 0; u32 ts_event_en = 0; - u32 sec_inc = 0; - u32 value = 0; - bool xmac; - - xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac; if (!(priv->dma_cap.time_stamp || priv->adv_ts)) { netdev_alert(priv->dev, "No support for HW time stamping\n"); @@ -789,42 +789,17 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) priv->hwts_rx_en = ((config.rx_filter == HWTSTAMP_FILTER_NONE) ? 0 : 1); priv->hwts_tx_en = config.tx_type == HWTSTAMP_TX_ON; - if (!priv->hwts_tx_en && !priv->hwts_rx_en) - stmmac_config_hw_tstamping(priv, priv->ptpaddr, 0); - else { - value = (PTP_TCR_TSENA | PTP_TCR_TSCFUPDT | PTP_TCR_TSCTRLSSR | - tstamp_all | ptp_v2 | ptp_over_ethernet | - ptp_over_ipv6_udp | ptp_over_ipv4_udp | ts_event_en | - ts_master_en | snap_type_sel); - stmmac_config_hw_tstamping(priv, priv->ptpaddr, value); - - /* program Sub Second Increment reg */ - stmmac_config_sub_second_increment(priv, - priv->ptpaddr, priv->plat->clk_ptp_rate, - xmac, &sec_inc); - temp = div_u64(1000000000ULL, sec_inc); - - /* Store sub second increment and flags for later use */ - priv->sub_second_inc = sec_inc; - priv->systime_flags = value; - - /* calculate default added value: - * formula is : - * addend = (2^32)/freq_div_ratio; - * where, freq_div_ratio = 1e9ns/sec_inc - */ - temp = (u64)(temp << 32); - priv->default_addend = div_u64(temp, priv->plat->clk_ptp_rate); - stmmac_config_addend(priv, priv->ptpaddr, priv->default_addend); - - /* initialize system time */ - ktime_get_real_ts64(&now); + priv->systime_flags = STMMAC_HWTS_ACTIVE; - /* lower 32 bits of tv_sec are safe until y2106 */ - stmmac_init_systime(priv, priv->ptpaddr, - (u32)now.tv_sec, now.tv_nsec); + if (priv->hwts_tx_en || priv->hwts_rx_en) { + priv->systime_flags |= tstamp_all | ptp_v2 | + ptp_over_ethernet | ptp_over_ipv6_udp | + ptp_over_ipv4_udp | ts_event_en | + ts_master_en | snap_type_sel; } + stmmac_config_hw_tstamping(priv, priv->ptpaddr, priv->systime_flags); + memcpy(&priv->tstamp_config, &config, sizeof(config)); return copy_to_user(ifr->ifr_data, &config, @@ -853,6 +828,66 @@ static int stmmac_hwtstamp_get(struct net_device *dev, struct ifreq *ifr) } /** + * stmmac_init_tstamp_counter - init hardware timestamping counter + * @priv: driver private structure + * @systime_flags: timestamping flags + * Description: + * Initialize hardware counter for packet timestamping. + * This is valid as long as the interface is open and not suspended. + * Will be rerun after resuming from suspend, case in which the timestamping + * flags updated by stmmac_hwtstamp_set() also need to be restored. + */ +int stmmac_init_tstamp_counter(struct stmmac_priv *priv, u32 systime_flags) +{ + bool xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac; + struct timespec64 now; + u32 sec_inc = 0; + u64 temp = 0; + int ret; + + if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp)) + return -EOPNOTSUPP; + + ret = clk_prepare_enable(priv->plat->clk_ptp_ref); + if (ret < 0) { + netdev_warn(priv->dev, + "failed to enable PTP reference clock: %pe\n", + ERR_PTR(ret)); + return ret; + } + + stmmac_config_hw_tstamping(priv, priv->ptpaddr, systime_flags); + priv->systime_flags = systime_flags; + + /* program Sub Second Increment reg */ + stmmac_config_sub_second_increment(priv, priv->ptpaddr, + priv->plat->clk_ptp_rate, + xmac, &sec_inc); + temp = div_u64(1000000000ULL, sec_inc); + + /* Store sub second increment for later use */ + priv->sub_second_inc = sec_inc; + + /* calculate default added value: + * formula is : + * addend = (2^32)/freq_div_ratio; + * where, freq_div_ratio = 1e9ns/sec_inc + */ + temp = (u64)(temp << 32); + priv->default_addend = div_u64(temp, priv->plat->clk_ptp_rate); + stmmac_config_addend(priv, priv->ptpaddr, priv->default_addend); + + /* initialize system time */ + ktime_get_real_ts64(&now); + + /* lower 32 bits of tv_sec are safe until y2106 */ + stmmac_init_systime(priv, priv->ptpaddr, (u32)now.tv_sec, now.tv_nsec); + + return 0; +} +EXPORT_SYMBOL_GPL(stmmac_init_tstamp_counter); + +/** * stmmac_init_ptp - init PTP * @priv: driver private structure * Description: this is to verify if the HW supports the PTPv1 or PTPv2. @@ -862,9 +897,11 @@ static int stmmac_hwtstamp_get(struct net_device *dev, struct ifreq *ifr) static int stmmac_init_ptp(struct stmmac_priv *priv) { bool xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac; + int ret; - if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp)) - return -EOPNOTSUPP; + ret = stmmac_init_tstamp_counter(priv, STMMAC_HWTS_ACTIVE); + if (ret) + return ret; priv->adv_ts = 0; /* Check if adv_ts can be enabled for dwmac 4.x / xgmac core */ @@ -3272,10 +3309,6 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) stmmac_mmc_setup(priv); if (init_ptp) { - ret = clk_prepare_enable(priv->plat->clk_ptp_ref); - if (ret < 0) - netdev_warn(priv->dev, "failed to enable PTP reference clock: %d\n", ret); - ret = stmmac_init_ptp(priv); if (ret == -EOPNOTSUPP) netdev_warn(priv->dev, "PTP not supported by HW\n"); @@ -3769,6 +3802,8 @@ int stmmac_release(struct net_device *dev) struct stmmac_priv *priv = netdev_priv(dev); u32 chan; + netif_tx_disable(dev); + if (device_may_wakeup(priv->device)) phylink_speed_down(priv->phylink, false); /* Stop and disconnect the PHY */ @@ -5161,12 +5196,13 @@ read_again: if (likely(!(status & rx_not_ls)) && (likely(priv->synopsys_id >= DWMAC_CORE_4_00) || unlikely(status != llc_snap))) { - if (buf2_len) + if (buf2_len) { buf2_len -= ETH_FCS_LEN; - else + len -= ETH_FCS_LEN; + } else if (buf1_len) { buf1_len -= ETH_FCS_LEN; - - len -= ETH_FCS_LEN; + len -= ETH_FCS_LEN; + } } if (!skb) { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 232ac98943cd..5d29f336315b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -816,7 +816,7 @@ static int __maybe_unused stmmac_pltfr_noirq_resume(struct device *dev) if (ret) return ret; - clk_prepare_enable(priv->plat->clk_ptp_ref); + stmmac_init_tstamp_counter(priv, priv->systime_flags); } return 0; diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index e2b332b54f06..7da2bb8a443c 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -31,6 +31,8 @@ #define AX_MTU 236 +/* some arch define END as assembly function ending, just undef it */ +#undef END /* SLIP/KISS protocol characters. */ #define END 0300 /* indicates end of frame */ #define ESC 0333 /* indicates byte stuffing */ diff --git a/drivers/net/ipa/ipa_cmd.c b/drivers/net/ipa/ipa_cmd.c index cff51731195a..d57472ea077f 100644 --- a/drivers/net/ipa/ipa_cmd.c +++ b/drivers/net/ipa/ipa_cmd.c @@ -661,22 +661,6 @@ void ipa_cmd_pipeline_clear_wait(struct ipa *ipa) wait_for_completion(&ipa->completion); } -void ipa_cmd_pipeline_clear(struct ipa *ipa) -{ - u32 count = ipa_cmd_pipeline_clear_count(); - struct gsi_trans *trans; - - trans = ipa_cmd_trans_alloc(ipa, count); - if (trans) { - ipa_cmd_pipeline_clear_add(trans); - gsi_trans_commit_wait(trans); - ipa_cmd_pipeline_clear_wait(ipa); - } else { - dev_err(&ipa->pdev->dev, - "error allocating %u entry tag transaction\n", count); - } -} - static struct ipa_cmd_info * ipa_cmd_info_alloc(struct ipa_endpoint *endpoint, u32 tre_count) { diff --git a/drivers/net/ipa/ipa_cmd.h b/drivers/net/ipa/ipa_cmd.h index 69cd085d427d..05ed7e42e184 100644 --- a/drivers/net/ipa/ipa_cmd.h +++ b/drivers/net/ipa/ipa_cmd.h @@ -164,12 +164,6 @@ u32 ipa_cmd_pipeline_clear_count(void); void ipa_cmd_pipeline_clear_wait(struct ipa *ipa); /** - * ipa_cmd_pipeline_clear() - Clear the hardware pipeline - * @ipa: - IPA pointer - */ -void ipa_cmd_pipeline_clear(struct ipa *ipa); - -/** * ipa_cmd_trans_alloc() - Allocate a transaction for the command TX endpoint * @ipa: IPA pointer * @tre_count: Number of elements in the transaction diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index ef790fd0ab56..03a170993420 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -1636,8 +1636,6 @@ void ipa_endpoint_suspend(struct ipa *ipa) if (ipa->modem_netdev) ipa_modem_suspend(ipa->modem_netdev); - ipa_cmd_pipeline_clear(ipa); - ipa_endpoint_suspend_one(ipa->name_map[IPA_ENDPOINT_AP_LAN_RX]); ipa_endpoint_suspend_one(ipa->name_map[IPA_ENDPOINT_AP_COMMAND_TX]); } diff --git a/drivers/net/ipa/ipa_main.c b/drivers/net/ipa/ipa_main.c index cdfa98a76e1f..a448ec198bee 100644 --- a/drivers/net/ipa/ipa_main.c +++ b/drivers/net/ipa/ipa_main.c @@ -28,6 +28,7 @@ #include "ipa_reg.h" #include "ipa_mem.h" #include "ipa_table.h" +#include "ipa_smp2p.h" #include "ipa_modem.h" #include "ipa_uc.h" #include "ipa_interrupt.h" @@ -801,6 +802,11 @@ static int ipa_remove(struct platform_device *pdev) struct device *dev = &pdev->dev; int ret; + /* Prevent the modem from triggering a call to ipa_setup(). This + * also ensures a modem-initiated setup that's underway completes. + */ + ipa_smp2p_irq_disable_setup(ipa); + ret = pm_runtime_get_sync(dev); if (WARN_ON(ret < 0)) goto out_power_put; diff --git a/drivers/net/ipa/ipa_modem.c b/drivers/net/ipa/ipa_modem.c index ad116bcc0580..d0ab4d70c303 100644 --- a/drivers/net/ipa/ipa_modem.c +++ b/drivers/net/ipa/ipa_modem.c @@ -339,9 +339,6 @@ int ipa_modem_stop(struct ipa *ipa) if (state != IPA_MODEM_STATE_RUNNING) return -EBUSY; - /* Prevent the modem from triggering a call to ipa_setup() */ - ipa_smp2p_disable(ipa); - /* Clean up the netdev and endpoints if it was started */ if (netdev) { struct ipa_priv *priv = netdev_priv(netdev); @@ -369,6 +366,9 @@ static void ipa_modem_crashed(struct ipa *ipa) struct device *dev = &ipa->pdev->dev; int ret; + /* Prevent the modem from triggering a call to ipa_setup() */ + ipa_smp2p_irq_disable_setup(ipa); + ret = pm_runtime_get_sync(dev); if (ret < 0) { dev_err(dev, "error %d getting power to handle crash\n", ret); diff --git a/drivers/net/ipa/ipa_smp2p.c b/drivers/net/ipa/ipa_smp2p.c index df7639c39d71..211233612039 100644 --- a/drivers/net/ipa/ipa_smp2p.c +++ b/drivers/net/ipa/ipa_smp2p.c @@ -53,7 +53,7 @@ * @setup_ready_irq: IPA interrupt triggered by modem to signal GSI ready * @power_on: Whether IPA power is on * @notified: Whether modem has been notified of power state - * @disabled: Whether setup ready interrupt handling is disabled + * @setup_disabled: Whether setup ready interrupt handler is disabled * @mutex: Mutex protecting ready-interrupt/shutdown interlock * @panic_notifier: Panic notifier structure */ @@ -67,7 +67,7 @@ struct ipa_smp2p { u32 setup_ready_irq; bool power_on; bool notified; - bool disabled; + bool setup_disabled; struct mutex mutex; struct notifier_block panic_notifier; }; @@ -155,11 +155,9 @@ static irqreturn_t ipa_smp2p_modem_setup_ready_isr(int irq, void *dev_id) struct device *dev; int ret; - mutex_lock(&smp2p->mutex); - - if (smp2p->disabled) - goto out_mutex_unlock; - smp2p->disabled = true; /* If any others arrive, ignore them */ + /* Ignore any (spurious) interrupts received after the first */ + if (smp2p->ipa->setup_complete) + return IRQ_HANDLED; /* Power needs to be active for setup */ dev = &smp2p->ipa->pdev->dev; @@ -176,8 +174,6 @@ static irqreturn_t ipa_smp2p_modem_setup_ready_isr(int irq, void *dev_id) out_power_put: pm_runtime_mark_last_busy(dev); (void)pm_runtime_put_autosuspend(dev); -out_mutex_unlock: - mutex_unlock(&smp2p->mutex); return IRQ_HANDLED; } @@ -313,7 +309,7 @@ void ipa_smp2p_exit(struct ipa *ipa) kfree(smp2p); } -void ipa_smp2p_disable(struct ipa *ipa) +void ipa_smp2p_irq_disable_setup(struct ipa *ipa) { struct ipa_smp2p *smp2p = ipa->smp2p; @@ -322,7 +318,10 @@ void ipa_smp2p_disable(struct ipa *ipa) mutex_lock(&smp2p->mutex); - smp2p->disabled = true; + if (!smp2p->setup_disabled) { + disable_irq(smp2p->setup_ready_irq); + smp2p->setup_disabled = true; + } mutex_unlock(&smp2p->mutex); } diff --git a/drivers/net/ipa/ipa_smp2p.h b/drivers/net/ipa/ipa_smp2p.h index 99a956789638..59cee31a7383 100644 --- a/drivers/net/ipa/ipa_smp2p.h +++ b/drivers/net/ipa/ipa_smp2p.h @@ -27,13 +27,12 @@ int ipa_smp2p_init(struct ipa *ipa, bool modem_init); void ipa_smp2p_exit(struct ipa *ipa); /** - * ipa_smp2p_disable() - Prevent "ipa-setup-ready" interrupt handling + * ipa_smp2p_irq_disable_setup() - Disable the "setup ready" interrupt * @ipa: IPA pointer * - * Prevent handling of the "setup ready" interrupt from the modem. - * This is used before initiating shutdown of the driver. + * Disable the "ipa-setup-ready" interrupt from the modem. */ -void ipa_smp2p_disable(struct ipa *ipa); +void ipa_smp2p_irq_disable_setup(struct ipa *ipa); /** * ipa_smp2p_notify_reset() - Reset modem notification state diff --git a/drivers/net/mdio/mdio-aspeed.c b/drivers/net/mdio/mdio-aspeed.c index cad820568f75..966c3b4ad59d 100644 --- a/drivers/net/mdio/mdio-aspeed.c +++ b/drivers/net/mdio/mdio-aspeed.c @@ -61,6 +61,13 @@ static int aspeed_mdio_read(struct mii_bus *bus, int addr, int regnum) iowrite32(ctrl, ctx->base + ASPEED_MDIO_CTRL); + rc = readl_poll_timeout(ctx->base + ASPEED_MDIO_CTRL, ctrl, + !(ctrl & ASPEED_MDIO_CTRL_FIRE), + ASPEED_MDIO_INTERVAL_US, + ASPEED_MDIO_TIMEOUT_US); + if (rc < 0) + return rc; + rc = readl_poll_timeout(ctx->base + ASPEED_MDIO_DATA, data, data & ASPEED_MDIO_DATA_IDLE, ASPEED_MDIO_INTERVAL_US, diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 3ad7397b8119..5904546acae6 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -710,6 +710,7 @@ static void phylink_resolve(struct work_struct *w) struct phylink_link_state link_state; struct net_device *ndev = pl->netdev; bool mac_config = false; + bool retrigger = false; bool cur_link_state; mutex_lock(&pl->state_mutex); @@ -723,6 +724,7 @@ static void phylink_resolve(struct work_struct *w) link_state.link = false; } else if (pl->mac_link_dropped) { link_state.link = false; + retrigger = true; } else { switch (pl->cur_link_an_mode) { case MLO_AN_PHY: @@ -739,6 +741,19 @@ static void phylink_resolve(struct work_struct *w) case MLO_AN_INBAND: phylink_mac_pcs_get_state(pl, &link_state); + /* The PCS may have a latching link-fail indicator. + * If the link was up, bring the link down and + * re-trigger the resolve. Otherwise, re-read the + * PCS state to get the current status of the link. + */ + if (!link_state.link) { + if (cur_link_state) + retrigger = true; + else + phylink_mac_pcs_get_state(pl, + &link_state); + } + /* If we have a phy, the "up" state is the union of * both the PHY and the MAC */ @@ -747,6 +762,15 @@ static void phylink_resolve(struct work_struct *w) /* Only update if the PHY link is up */ if (pl->phydev && pl->phy_state.link) { + /* If the interface has changed, force a + * link down event if the link isn't already + * down, and re-resolve. + */ + if (link_state.interface != + pl->phy_state.interface) { + retrigger = true; + link_state.link = false; + } link_state.interface = pl->phy_state.interface; /* If we have a PHY, we need to update with @@ -789,7 +813,7 @@ static void phylink_resolve(struct work_struct *w) else phylink_link_up(pl, link_state); } - if (!link_state.link && pl->mac_link_dropped) { + if (!link_state.link && retrigger) { pl->mac_link_dropped = false; queue_work(system_power_efficient_wq, &pl->resolve); } diff --git a/drivers/net/slip/slip.h b/drivers/net/slip/slip.h index c420e5948522..3d7f88b330c1 100644 --- a/drivers/net/slip/slip.h +++ b/drivers/net/slip/slip.h @@ -40,6 +40,8 @@ insmod -oslip_maxdev=nnn */ #define SL_MTU 296 /* 296; I am used to 600- FvK */ +/* some arch define END as assembly function ending, just undef it */ +#undef END /* SLIP protocol characters. */ #define END 0300 /* indicates end of frame */ #define ESC 0333 /* indicates byte stuffing */ diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 20fe4cd8f784..abe0149ed917 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -1050,6 +1050,14 @@ static const struct net_device_ops smsc95xx_netdev_ops = { .ndo_set_features = smsc95xx_set_features, }; +static void smsc95xx_handle_link_change(struct net_device *net) +{ + struct usbnet *dev = netdev_priv(net); + + phy_print_status(net->phydev); + usbnet_defer_kevent(dev, EVENT_LINK_CHANGE); +} + static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf) { struct smsc95xx_priv *pdata; @@ -1154,6 +1162,17 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf) dev->net->min_mtu = ETH_MIN_MTU; dev->net->max_mtu = ETH_DATA_LEN; dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len; + + ret = phy_connect_direct(dev->net, pdata->phydev, + &smsc95xx_handle_link_change, + PHY_INTERFACE_MODE_MII); + if (ret) { + netdev_err(dev->net, "can't attach PHY to %s\n", pdata->mdiobus->id); + goto unregister_mdio; + } + + phy_attached_info(dev->net->phydev); + return 0; unregister_mdio: @@ -1171,47 +1190,25 @@ static void smsc95xx_unbind(struct usbnet *dev, struct usb_interface *intf) { struct smsc95xx_priv *pdata = dev->driver_priv; + phy_disconnect(dev->net->phydev); mdiobus_unregister(pdata->mdiobus); mdiobus_free(pdata->mdiobus); netif_dbg(dev, ifdown, dev->net, "free pdata\n"); kfree(pdata); } -static void smsc95xx_handle_link_change(struct net_device *net) -{ - struct usbnet *dev = netdev_priv(net); - - phy_print_status(net->phydev); - usbnet_defer_kevent(dev, EVENT_LINK_CHANGE); -} - static int smsc95xx_start_phy(struct usbnet *dev) { - struct smsc95xx_priv *pdata = dev->driver_priv; - struct net_device *net = dev->net; - int ret; + phy_start(dev->net->phydev); - ret = smsc95xx_reset(dev); - if (ret < 0) - return ret; - - ret = phy_connect_direct(net, pdata->phydev, - &smsc95xx_handle_link_change, - PHY_INTERFACE_MODE_MII); - if (ret) { - netdev_err(net, "can't attach PHY to %s\n", pdata->mdiobus->id); - return ret; - } - - phy_attached_info(net->phydev); - phy_start(net->phydev); return 0; } -static int smsc95xx_disconnect_phy(struct usbnet *dev) +static int smsc95xx_stop(struct usbnet *dev) { - phy_stop(dev->net->phydev); - phy_disconnect(dev->net->phydev); + if (dev->net->phydev) + phy_stop(dev->net->phydev); + return 0; } @@ -1966,7 +1963,7 @@ static const struct driver_info smsc95xx_info = { .unbind = smsc95xx_unbind, .link_reset = smsc95xx_link_reset, .reset = smsc95xx_start_phy, - .stop = smsc95xx_disconnect_phy, + .stop = smsc95xx_stop, .rx_fixup = smsc95xx_rx_fixup, .tx_fixup = smsc95xx_tx_fixup, .status = smsc95xx_status, diff --git a/drivers/nfc/virtual_ncidev.c b/drivers/nfc/virtual_ncidev.c index 221fa3bb8705..f577449e4935 100644 --- a/drivers/nfc/virtual_ncidev.c +++ b/drivers/nfc/virtual_ncidev.c @@ -202,7 +202,7 @@ static int __init virtual_ncidev_init(void) miscdev.minor = MISC_DYNAMIC_MINOR; miscdev.name = "virtual_nci"; miscdev.fops = &virtual_ncidev_fops; - miscdev.mode = S_IALLUGO; + miscdev.mode = 0600; return misc_register(&miscdev); } diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index ae04968a3a47..9afd34a2d36c 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -37,6 +37,7 @@ #define PTP_MSGTYPE_PDELAY_RESP 0x3 #define PTP_EV_PORT 319 +#define PTP_GEN_PORT 320 #define PTP_GEN_BIT 0x08 /* indicates general message, if set in message type */ #define OFF_PTP_SOURCE_UUID 22 /* PTPv1 only */ diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index c412dde4d67d..83b8070d1cc9 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -485,6 +485,7 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); void fib6_nh_release(struct fib6_nh *fib6_nh); +void fib6_nh_release_dsts(struct fib6_nh *fib6_nh); int call_fib6_entry_notifiers(struct net *net, enum fib_event_type event_type, diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index afbce90c4480..45e0339be6fa 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -47,6 +47,7 @@ struct ipv6_stub { struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); void (*fib6_nh_release)(struct fib6_nh *fib6_nh); + void (*fib6_nh_release_dsts)(struct fib6_nh *fib6_nh); void (*fib6_update_sernum)(struct net *net, struct fib6_info *rt); int (*ip6_del_rt)(struct net *net, struct fib6_info *rt, bool skip_notify); void (*fib6_rt_update)(struct net *net, struct fib6_info *rt, diff --git a/include/net/nl802154.h b/include/net/nl802154.h index ddcee128f5d9..145acb8f2509 100644 --- a/include/net/nl802154.h +++ b/include/net/nl802154.h @@ -19,6 +19,8 @@ * */ +#include <linux/types.h> + #define NL802154_GENL_NAME "nl802154" enum nl802154_commands { @@ -150,10 +152,9 @@ enum nl802154_attrs { }; enum nl802154_iftype { - /* for backwards compatibility TODO */ - NL802154_IFTYPE_UNSPEC = -1, + NL802154_IFTYPE_UNSPEC = (~(__u32)0), - NL802154_IFTYPE_NODE, + NL802154_IFTYPE_NODE = 0, NL802154_IFTYPE_MONITOR, NL802154_IFTYPE_COORD, diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index eeb1142aa1b1..4d1dfa1136b2 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -703,6 +703,8 @@ int ocelot_vcap_filter_add(struct ocelot *ocelot, struct netlink_ext_ack *extack); int ocelot_vcap_filter_del(struct ocelot *ocelot, struct ocelot_vcap_filter *rule); +int ocelot_vcap_filter_replace(struct ocelot *ocelot, + struct ocelot_vcap_filter *filter); struct ocelot_vcap_filter * ocelot_vcap_block_find_filter_by_id(struct ocelot_vcap_block *block, unsigned long cookie, bool tc_offload); diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index a3a0a5e994f5..abaa5d96ded2 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -184,9 +184,6 @@ int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack) if (err) goto out_unregister_netdev; - /* Account for reference in struct vlan_dev_priv */ - dev_hold(real_dev); - vlan_stacked_transfer_operstate(real_dev, dev, vlan); linkwatch_fire_event(dev); /* _MUST_ call rfc2863_policy() */ diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index ab6dee28536d..a54535cbcf4c 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -615,6 +615,9 @@ static int vlan_dev_init(struct net_device *dev) if (!vlan->vlan_pcpu_stats) return -ENOMEM; + /* Get vlan's reference to real_dev */ + dev_hold(real_dev); + return 0; } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 47931c8be04b..72ba027c34cf 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1779,6 +1779,7 @@ int neigh_table_clear(int index, struct neigh_table *tbl) { neigh_tables[index] = NULL; /* It is not clean... Fix it to unload IPv6 module safely */ + cancel_delayed_work_sync(&tbl->managed_work); cancel_delayed_work_sync(&tbl->gc_work); del_timer_sync(&tbl->proxy_timer); pneigh_queue_purge(&tbl->proxy_queue); diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 65e9bc1058b5..20bcf86970ff 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1719,7 +1719,7 @@ static noinline_for_stack int ethtool_set_coalesce(struct net_device *dev, struct ethtool_coalesce coalesce; int ret; - if (!dev->ethtool_ops->set_coalesce && !dev->ethtool_ops->get_coalesce) + if (!dev->ethtool_ops->set_coalesce || !dev->ethtool_ops->get_coalesce) return -EOPNOTSUPP; ret = dev->ethtool_ops->get_coalesce(dev, &coalesce, &kernel_coalesce, diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 9e8100728d46..5dbd4b5505eb 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -1899,15 +1899,36 @@ static void remove_nexthop(struct net *net, struct nexthop *nh, /* if any FIB entries reference this nexthop, any dst entries * need to be regenerated */ -static void nh_rt_cache_flush(struct net *net, struct nexthop *nh) +static void nh_rt_cache_flush(struct net *net, struct nexthop *nh, + struct nexthop *replaced_nh) { struct fib6_info *f6i; + struct nh_group *nhg; + int i; if (!list_empty(&nh->fi_list)) rt_cache_flush(net); list_for_each_entry(f6i, &nh->f6i_list, nh_list) ipv6_stub->fib6_update_sernum(net, f6i); + + /* if an IPv6 group was replaced, we have to release all old + * dsts to make sure all refcounts are released + */ + if (!replaced_nh->is_group) + return; + + /* new dsts must use only the new nexthop group */ + synchronize_net(); + + nhg = rtnl_dereference(replaced_nh->nh_grp); + for (i = 0; i < nhg->num_nh; i++) { + struct nh_grp_entry *nhge = &nhg->nh_entries[i]; + struct nh_info *nhi = rtnl_dereference(nhge->nh->nh_info); + + if (nhi->family == AF_INET6) + ipv6_stub->fib6_nh_release_dsts(&nhi->fib6_nh); + } } static int replace_nexthop_grp(struct net *net, struct nexthop *old, @@ -2247,7 +2268,7 @@ static int replace_nexthop(struct net *net, struct nexthop *old, err = replace_nexthop_single(net, old, new, extack); if (!err) { - nh_rt_cache_flush(net, old); + nh_rt_cache_flush(net, old, new); __remove_nexthop(net, new, NULL); nexthop_put(new); @@ -2544,11 +2565,15 @@ static int nh_create_ipv6(struct net *net, struct nexthop *nh, /* sets nh_dev if successful */ err = ipv6_stub->fib6_nh_init(net, fib6_nh, &fib6_cfg, GFP_KERNEL, extack); - if (err) + if (err) { + /* IPv6 is not enabled, don't call fib6_nh_release */ + if (err == -EAFNOSUPPORT) + goto out; ipv6_stub->fib6_nh_release(fib6_nh); - else + } else { nh->nh_flags = fib6_nh->fib_nh_flags; - + } +out: return err; } diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 5e9d9c51164c..e07837e23b3f 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -330,8 +330,6 @@ static void cubictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) return; if (tcp_in_slow_start(tp)) { - if (hystart && after(ack, ca->end_seq)) - bictcp_hystart_reset(sk); acked = tcp_slow_start(tp, acked); if (!acked) return; @@ -391,6 +389,9 @@ static void hystart_update(struct sock *sk, u32 delay) struct bictcp *ca = inet_csk_ca(sk); u32 threshold; + if (after(tp->snd_una, ca->end_seq)) + bictcp_hystart_reset(sk); + if (hystart_detect & HYSTART_ACK_TRAIN) { u32 now = bictcp_clock_us(sk); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 0c4da163535a..dab4a047590b 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -1026,6 +1026,7 @@ static const struct ipv6_stub ipv6_stub_impl = { .ip6_mtu_from_fib6 = ip6_mtu_from_fib6, .fib6_nh_init = fib6_nh_init, .fib6_nh_release = fib6_nh_release, + .fib6_nh_release_dsts = fib6_nh_release_dsts, .fib6_update_sernum = fib6_update_sernum_stub, .fib6_rt_update = fib6_rt_update, .ip6_del_rt = ip6_del_rt, diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 2f044a49afa8..ff4e83e2a506 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -174,7 +174,7 @@ static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) /* Policy lookup after SNAT yielded a new policy */ if (skb_dst(skb)->xfrm) { - IPCB(skb)->flags |= IPSKB_REROUTED; + IP6CB(skb)->flags |= IP6SKB_REROUTED; return dst_output(net, sk, skb); } #endif diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 3ae25b8ffbd6..42d60c76d30a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3680,6 +3680,25 @@ void fib6_nh_release(struct fib6_nh *fib6_nh) fib_nh_common_release(&fib6_nh->nh_common); } +void fib6_nh_release_dsts(struct fib6_nh *fib6_nh) +{ + int cpu; + + if (!fib6_nh->rt6i_pcpu) + return; + + for_each_possible_cpu(cpu) { + struct rt6_info *pcpu_rt, **ppcpu_rt; + + ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu); + pcpu_rt = xchg(ppcpu_rt, NULL); + if (pcpu_rt) { + dst_dev_put(&pcpu_rt->dst); + dst_release(&pcpu_rt->dst); + } + } +} + static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 7c3420afb1a0..fe98e4f475ba 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -422,28 +422,6 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, return false; } -/* MP_JOIN client subflow must wait for 4th ack before sending any data: - * TCP can't schedule delack timer before the subflow is fully established. - * MPTCP uses the delack timer to do 3rd ack retransmissions - */ -static void schedule_3rdack_retransmission(struct sock *sk) -{ - struct inet_connection_sock *icsk = inet_csk(sk); - struct tcp_sock *tp = tcp_sk(sk); - unsigned long timeout; - - /* reschedule with a timeout above RTT, as we must look only for drop */ - if (tp->srtt_us) - timeout = tp->srtt_us << 1; - else - timeout = TCP_TIMEOUT_INIT; - - WARN_ON_ONCE(icsk->icsk_ack.pending & ICSK_ACK_TIMER); - icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER; - icsk->icsk_ack.timeout = timeout; - sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout); -} - static void clear_3rdack_retransmission(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -526,7 +504,15 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, *size = TCPOLEN_MPTCP_MPJ_ACK; pr_debug("subflow=%p", subflow); - schedule_3rdack_retransmission(sk); + /* we can use the full delegate action helper only from BH context + * If we are in process context - sk is flushing the backlog at + * socket lock release time - just set the appropriate flag, will + * be handled by the release callback + */ + if (sock_owned_by_user(sk)) + set_bit(MPTCP_DELEGATE_ACK, &subflow->delegated_status); + else + mptcp_subflow_delegate(subflow, MPTCP_DELEGATE_ACK); return true; } return false; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index b7e32e316738..c82a76d2d0bf 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1596,7 +1596,8 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk) if (!xmit_ssk) goto out; if (xmit_ssk != ssk) { - mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk)); + mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk), + MPTCP_DELEGATE_SEND); goto out; } @@ -2943,7 +2944,7 @@ void __mptcp_check_push(struct sock *sk, struct sock *ssk) if (xmit_ssk == ssk) __mptcp_subflow_push_pending(sk, ssk); else if (xmit_ssk) - mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk)); + mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk), MPTCP_DELEGATE_SEND); } else { set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags); } @@ -2993,18 +2994,50 @@ static void mptcp_release_cb(struct sock *sk) __mptcp_update_rmem(sk); } +/* MP_JOIN client subflow must wait for 4th ack before sending any data: + * TCP can't schedule delack timer before the subflow is fully established. + * MPTCP uses the delack timer to do 3rd ack retransmissions + */ +static void schedule_3rdack_retransmission(struct sock *ssk) +{ + struct inet_connection_sock *icsk = inet_csk(ssk); + struct tcp_sock *tp = tcp_sk(ssk); + unsigned long timeout; + + if (mptcp_subflow_ctx(ssk)->fully_established) + return; + + /* reschedule with a timeout above RTT, as we must look only for drop */ + if (tp->srtt_us) + timeout = usecs_to_jiffies(tp->srtt_us >> (3 - 1)); + else + timeout = TCP_TIMEOUT_INIT; + timeout += jiffies; + + WARN_ON_ONCE(icsk->icsk_ack.pending & ICSK_ACK_TIMER); + icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER; + icsk->icsk_ack.timeout = timeout; + sk_reset_timer(ssk, &icsk->icsk_delack_timer, timeout); +} + void mptcp_subflow_process_delegated(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = subflow->conn; - mptcp_data_lock(sk); - if (!sock_owned_by_user(sk)) - __mptcp_subflow_push_pending(sk, ssk); - else - set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags); - mptcp_data_unlock(sk); - mptcp_subflow_delegated_done(subflow); + if (test_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status)) { + mptcp_data_lock(sk); + if (!sock_owned_by_user(sk)) + __mptcp_subflow_push_pending(sk, ssk); + else + set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags); + mptcp_data_unlock(sk); + mptcp_subflow_delegated_done(subflow, MPTCP_DELEGATE_SEND); + } + if (test_bit(MPTCP_DELEGATE_ACK, &subflow->delegated_status)) { + schedule_3rdack_retransmission(ssk); + mptcp_subflow_delegated_done(subflow, MPTCP_DELEGATE_ACK); + } } static int mptcp_hash(struct sock *sk) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 67a61ac48b20..d87cc040352e 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -387,6 +387,7 @@ struct mptcp_delegated_action { DECLARE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions); #define MPTCP_DELEGATE_SEND 0 +#define MPTCP_DELEGATE_ACK 1 /* MPTCP subflow context */ struct mptcp_subflow_context { @@ -492,23 +493,23 @@ static inline void mptcp_add_pending_subflow(struct mptcp_sock *msk, void mptcp_subflow_process_delegated(struct sock *ssk); -static inline void mptcp_subflow_delegate(struct mptcp_subflow_context *subflow) +static inline void mptcp_subflow_delegate(struct mptcp_subflow_context *subflow, int action) { struct mptcp_delegated_action *delegated; bool schedule; + /* the caller held the subflow bh socket lock */ + lockdep_assert_in_softirq(); + /* The implied barrier pairs with mptcp_subflow_delegated_done(), and * ensures the below list check sees list updates done prior to status * bit changes */ - if (!test_and_set_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status)) { + if (!test_and_set_bit(action, &subflow->delegated_status)) { /* still on delegated list from previous scheduling */ if (!list_empty(&subflow->delegated_node)) return; - /* the caller held the subflow bh socket lock */ - lockdep_assert_in_softirq(); - delegated = this_cpu_ptr(&mptcp_delegated_actions); schedule = list_empty(&delegated->head); list_add_tail(&subflow->delegated_node, &delegated->head); @@ -533,16 +534,16 @@ mptcp_subflow_delegated_next(struct mptcp_delegated_action *delegated) static inline bool mptcp_subflow_has_delegated_action(const struct mptcp_subflow_context *subflow) { - return test_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status); + return !!READ_ONCE(subflow->delegated_status); } -static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *subflow) +static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *subflow, int action) { /* pairs with mptcp_subflow_delegate, ensures delegate_node is updated before * touching the status bit */ smp_wmb(); - clear_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status); + clear_bit(action, &subflow->delegated_status); } int mptcp_is_enabled(const struct net *net); diff --git a/net/ncsi/ncsi-cmd.c b/net/ncsi/ncsi-cmd.c index ba9ae482141b..dda8b76b7798 100644 --- a/net/ncsi/ncsi-cmd.c +++ b/net/ncsi/ncsi-cmd.c @@ -18,6 +18,8 @@ #include "internal.h" #include "ncsi-pkt.h" +static const int padding_bytes = 26; + u32 ncsi_calculate_checksum(unsigned char *data, int len) { u32 checksum = 0; @@ -213,12 +215,17 @@ static int ncsi_cmd_handler_oem(struct sk_buff *skb, { struct ncsi_cmd_oem_pkt *cmd; unsigned int len; + int payload; + /* NC-SI spec DSP_0222_1.2.0, section 8.2.2.2 + * requires payload to be padded with 0 to + * 32-bit boundary before the checksum field. + * Ensure the padding bytes are accounted for in + * skb allocation + */ + payload = ALIGN(nca->payload, 4); len = sizeof(struct ncsi_cmd_pkt_hdr) + 4; - if (nca->payload < 26) - len += 26; - else - len += nca->payload; + len += max(payload, padding_bytes); cmd = skb_put_zero(skb, len); memcpy(&cmd->mfr_id, nca->data, nca->payload); @@ -272,6 +279,7 @@ static struct ncsi_request *ncsi_alloc_command(struct ncsi_cmd_arg *nca) struct net_device *dev = nd->dev; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; + int payload; int len = hlen + tlen; struct sk_buff *skb; struct ncsi_request *nr; @@ -281,14 +289,14 @@ static struct ncsi_request *ncsi_alloc_command(struct ncsi_cmd_arg *nca) return NULL; /* NCSI command packet has 16-bytes header, payload, 4 bytes checksum. + * Payload needs padding so that the checksum field following payload is + * aligned to 32-bit boundary. * The packet needs padding if its payload is less than 26 bytes to * meet 64 bytes minimal ethernet frame length. */ len += sizeof(struct ncsi_cmd_pkt_hdr) + 4; - if (nca->payload < 26) - len += 26; - else - len += nca->payload; + payload = ALIGN(nca->payload, 4); + len += max(payload, padding_bytes); /* Allocate skb */ skb = alloc_skb(len, GFP_ATOMIC); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index e93c937a8bf0..51ad557a525b 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1919,7 +1919,6 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; int ret, pkts; - int conn_reuse_mode; struct sock *sk; int af = state->pf; @@ -1997,15 +1996,16 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, ipvs, af, skb, &iph); - conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); - if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) { + if (!iph.fragoffs && is_new_conn(skb, &iph) && cp) { + int conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); bool old_ct = false, resched = false; if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest && unlikely(!atomic_read(&cp->dest->weight))) { resched = true; old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); - } else if (is_new_conn_expected(cp, conn_reuse_mode)) { + } else if (conn_reuse_mode && + is_new_conn_expected(cp, conn_reuse_mode)) { old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); if (!atomic_read(&cp->n_control)) { resched = true; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index f1e5443fe7c7..c7708bde057c 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1011,11 +1011,9 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) CTA_TUPLE_REPLY, filter->family, &filter->zone, - filter->orig_flags); - if (err < 0) { - err = -EINVAL; + filter->reply_flags); + if (err < 0) goto err_filter; - } } return filter; diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index d6bf1b2cd541..b561e0a44a45 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -65,11 +65,11 @@ static void nf_flow_rule_lwt_match(struct nf_flow_match *match, sizeof(struct in6_addr)); if (memcmp(&key->enc_ipv6.src, &in6addr_any, sizeof(struct in6_addr))) - memset(&key->enc_ipv6.src, 0xff, + memset(&mask->enc_ipv6.src, 0xff, sizeof(struct in6_addr)); if (memcmp(&key->enc_ipv6.dst, &in6addr_any, sizeof(struct in6_addr))) - memset(&key->enc_ipv6.dst, 0xff, + memset(&mask->enc_ipv6.dst, 0xff, sizeof(struct in6_addr)); enc_keys |= BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS); key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index cbfe4e4a4ad7..bd689938a2e0 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -22,7 +22,6 @@ #include <linux/icmpv6.h> #include <linux/ip.h> #include <linux/ipv6.h> -#include <linux/ip.h> #include <net/sctp/checksum.h> static bool nft_payload_rebuild_vlan_hdr(const struct sk_buff *skb, int mac_off, diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index 2f7cf5ecebf4..0f8bb0bf558f 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -85,9 +85,9 @@ static ssize_t idletimer_tg_show(struct device *dev, mutex_unlock(&list_mutex); if (time_after(expires, jiffies) || ktimespec.tv_sec > 0) - return snprintf(buf, PAGE_SIZE, "%ld\n", time_diff); + return sysfs_emit(buf, "%ld\n", time_diff); - return snprintf(buf, PAGE_SIZE, "0\n"); + return sysfs_emit(buf, "0\n"); } static void idletimer_tg_work(struct work_struct *work) diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index 0eae9ff5edf6..e007fc75ef2f 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -665,12 +665,14 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, q->classes[i].deficit = quanta[i]; } } + for (i = q->nbands; i < oldbands; i++) { + qdisc_tree_flush_backlog(q->classes[i].qdisc); + if (i >= q->nstrict) + list_del(&q->classes[i].alist); + } q->nstrict = nstrict; memcpy(q->prio2band, priomap, sizeof(priomap)); - for (i = q->nbands; i < oldbands; i++) - qdisc_tree_flush_backlog(q->classes[i].qdisc); - for (i = 0; i < q->nbands; i++) q->classes[i].quantum = quanta[i]; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index b61c802e3bf3..230072f9ec48 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -585,7 +585,7 @@ static void smc_switch_to_fallback(struct smc_sock *smc, int reason_code) * to clcsocket->wq during the fallback. */ spin_lock_irqsave(&smc_wait->lock, flags); - spin_lock(&clc_wait->lock); + spin_lock_nested(&clc_wait->lock, SINGLE_DEPTH_NESTING); list_splice_init(&smc_wait->head, &clc_wait->head); spin_unlock(&clc_wait->lock); spin_unlock_irqrestore(&smc_wait->lock, flags); @@ -2134,8 +2134,10 @@ static int smc_listen(struct socket *sock, int backlog) smc->clcsock->sk->sk_user_data = (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); rc = kernel_listen(smc->clcsock, backlog); - if (rc) + if (rc) { + smc->clcsock->sk->sk_data_ready = smc->clcsk_data_ready; goto out; + } sk->sk_max_ack_backlog = backlog; sk->sk_ack_backlog = 0; sk->sk_state = SMC_LISTEN; @@ -2368,8 +2370,10 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, static int smc_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; + bool do_shutdown = true; struct smc_sock *smc; int rc = -EINVAL; + int old_state; int rc1 = 0; smc = smc_sk(sk); @@ -2396,7 +2400,11 @@ static int smc_shutdown(struct socket *sock, int how) } switch (how) { case SHUT_RDWR: /* shutdown in both directions */ + old_state = sk->sk_state; rc = smc_close_active(smc); + if (old_state == SMC_ACTIVE && + sk->sk_state == SMC_PEERCLOSEWAIT1) + do_shutdown = false; break; case SHUT_WR: rc = smc_close_shutdown_write(smc); @@ -2406,7 +2414,7 @@ static int smc_shutdown(struct socket *sock, int how) /* nothing more to do because peer is not involved */ break; } - if (smc->clcsock) + if (do_shutdown && smc->clcsock) rc1 = kernel_sock_shutdown(smc->clcsock, how); /* map sock_shutdown_cmd constants to sk_shutdown value range */ sk->sk_shutdown |= how + 1; diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index 0f9ffba07d26..3715d2f5ad55 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -228,6 +228,12 @@ again: /* send close request */ rc = smc_close_final(conn); sk->sk_state = SMC_PEERCLOSEWAIT1; + + /* actively shutdown clcsock before peer close it, + * prevent peer from entering TIME_WAIT state. + */ + if (smc->clcsock && smc->clcsock->sk) + rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); } else { /* peer event has changed the state */ goto again; @@ -354,9 +360,9 @@ static void smc_close_passive_work(struct work_struct *work) if (rxflags->peer_conn_abort) { /* peer has not received all data */ smc_close_passive_abort_received(smc); - release_sock(&smc->sk); + release_sock(sk); cancel_delayed_work_sync(&conn->tx_work); - lock_sock(&smc->sk); + lock_sock(sk); goto wakeup; } diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 25ebd30feecd..bb52c8b5f148 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1672,14 +1672,26 @@ static void smc_link_down_work(struct work_struct *work) mutex_unlock(&lgr->llc_conf_mutex); } -/* Determine vlan of internal TCP socket. - * @vlan_id: address to store the determined vlan id into - */ +static int smc_vlan_by_tcpsk_walk(struct net_device *lower_dev, + struct netdev_nested_priv *priv) +{ + unsigned short *vlan_id = (unsigned short *)priv->data; + + if (is_vlan_dev(lower_dev)) { + *vlan_id = vlan_dev_vlan_id(lower_dev); + return 1; + } + + return 0; +} + +/* Determine vlan of internal TCP socket. */ int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini) { struct dst_entry *dst = sk_dst_get(clcsock->sk); + struct netdev_nested_priv priv; struct net_device *ndev; - int i, nest_lvl, rc = 0; + int rc = 0; ini->vlan_id = 0; if (!dst) { @@ -1697,20 +1709,9 @@ int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini) goto out_rel; } + priv.data = (void *)&ini->vlan_id; rtnl_lock(); - nest_lvl = ndev->lower_level; - for (i = 0; i < nest_lvl; i++) { - struct list_head *lower = &ndev->adj_list.lower; - - if (list_empty(lower)) - break; - lower = lower->next; - ndev = (struct net_device *)netdev_lower_get_next(ndev, &lower); - if (is_vlan_dev(ndev)) { - ini->vlan_id = vlan_dev_vlan_id(ndev); - break; - } - } + netdev_walk_all_lower_dev(ndev, smc_vlan_by_tcpsk_walk, &priv); rtnl_unlock(); out_rel: diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index acfba9f1ba72..6bc2879ba637 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -61,7 +61,7 @@ static DEFINE_MUTEX(tcpv6_prot_mutex); static const struct proto *saved_tcpv4_prot; static DEFINE_MUTEX(tcpv4_prot_mutex); static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG][TLS_NUM_CONFIG]; -static struct proto_ops tls_sw_proto_ops; +static struct proto_ops tls_proto_ops[TLS_NUM_PROTS][TLS_NUM_CONFIG][TLS_NUM_CONFIG]; static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], const struct proto *base); @@ -71,6 +71,8 @@ void update_sk_prot(struct sock *sk, struct tls_context *ctx) WRITE_ONCE(sk->sk_prot, &tls_prots[ip_ver][ctx->tx_conf][ctx->rx_conf]); + WRITE_ONCE(sk->sk_socket->ops, + &tls_proto_ops[ip_ver][ctx->tx_conf][ctx->rx_conf]); } int wait_on_pending_writer(struct sock *sk, long *timeo) @@ -669,8 +671,6 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval, if (tx) { ctx->sk_write_space = sk->sk_write_space; sk->sk_write_space = tls_write_space; - } else { - sk->sk_socket->ops = &tls_sw_proto_ops; } goto out; @@ -728,6 +728,39 @@ struct tls_context *tls_ctx_create(struct sock *sk) return ctx; } +static void build_proto_ops(struct proto_ops ops[TLS_NUM_CONFIG][TLS_NUM_CONFIG], + const struct proto_ops *base) +{ + ops[TLS_BASE][TLS_BASE] = *base; + + ops[TLS_SW ][TLS_BASE] = ops[TLS_BASE][TLS_BASE]; + ops[TLS_SW ][TLS_BASE].sendpage_locked = tls_sw_sendpage_locked; + + ops[TLS_BASE][TLS_SW ] = ops[TLS_BASE][TLS_BASE]; + ops[TLS_BASE][TLS_SW ].splice_read = tls_sw_splice_read; + + ops[TLS_SW ][TLS_SW ] = ops[TLS_SW ][TLS_BASE]; + ops[TLS_SW ][TLS_SW ].splice_read = tls_sw_splice_read; + +#ifdef CONFIG_TLS_DEVICE + ops[TLS_HW ][TLS_BASE] = ops[TLS_BASE][TLS_BASE]; + ops[TLS_HW ][TLS_BASE].sendpage_locked = NULL; + + ops[TLS_HW ][TLS_SW ] = ops[TLS_BASE][TLS_SW ]; + ops[TLS_HW ][TLS_SW ].sendpage_locked = NULL; + + ops[TLS_BASE][TLS_HW ] = ops[TLS_BASE][TLS_SW ]; + + ops[TLS_SW ][TLS_HW ] = ops[TLS_SW ][TLS_SW ]; + + ops[TLS_HW ][TLS_HW ] = ops[TLS_HW ][TLS_SW ]; + ops[TLS_HW ][TLS_HW ].sendpage_locked = NULL; +#endif +#ifdef CONFIG_TLS_TOE + ops[TLS_HW_RECORD][TLS_HW_RECORD] = *base; +#endif +} + static void tls_build_proto(struct sock *sk) { int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4; @@ -739,6 +772,8 @@ static void tls_build_proto(struct sock *sk) mutex_lock(&tcpv6_prot_mutex); if (likely(prot != saved_tcpv6_prot)) { build_protos(tls_prots[TLSV6], prot); + build_proto_ops(tls_proto_ops[TLSV6], + sk->sk_socket->ops); smp_store_release(&saved_tcpv6_prot, prot); } mutex_unlock(&tcpv6_prot_mutex); @@ -749,6 +784,8 @@ static void tls_build_proto(struct sock *sk) mutex_lock(&tcpv4_prot_mutex); if (likely(prot != saved_tcpv4_prot)) { build_protos(tls_prots[TLSV4], prot); + build_proto_ops(tls_proto_ops[TLSV4], + sk->sk_socket->ops); smp_store_release(&saved_tcpv4_prot, prot); } mutex_unlock(&tcpv4_prot_mutex); @@ -959,10 +996,6 @@ static int __init tls_register(void) if (err) return err; - tls_sw_proto_ops = inet_stream_ops; - tls_sw_proto_ops.splice_read = tls_sw_splice_read; - tls_sw_proto_ops.sendpage_locked = tls_sw_sendpage_locked; - tls_device_init(); tcp_register_ulp(&tcp_tls_ulp_ops); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index d81564078557..d3e7ff90889e 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2005,6 +2005,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, struct sock *sk = sock->sk; struct sk_buff *skb; ssize_t copied = 0; + bool from_queue; int err = 0; long timeo; int chunk; @@ -2014,25 +2015,28 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, timeo = sock_rcvtimeo(sk, flags & SPLICE_F_NONBLOCK); - skb = tls_wait_data(sk, NULL, flags & SPLICE_F_NONBLOCK, timeo, &err); - if (!skb) - goto splice_read_end; - - if (!ctx->decrypted) { - err = decrypt_skb_update(sk, skb, NULL, &chunk, &zc, false); - - /* splice does not support reading control messages */ - if (ctx->control != TLS_RECORD_TYPE_DATA) { - err = -EINVAL; + from_queue = !skb_queue_empty(&ctx->rx_list); + if (from_queue) { + skb = __skb_dequeue(&ctx->rx_list); + } else { + skb = tls_wait_data(sk, NULL, flags & SPLICE_F_NONBLOCK, timeo, + &err); + if (!skb) goto splice_read_end; - } + err = decrypt_skb_update(sk, skb, NULL, &chunk, &zc, false); if (err < 0) { tls_err_abort(sk, -EBADMSG); goto splice_read_end; } - ctx->decrypted = 1; } + + /* splice does not support reading control messages */ + if (ctx->control != TLS_RECORD_TYPE_DATA) { + err = -EINVAL; + goto splice_read_end; + } + rxm = strp_msg(skb); chunk = min_t(unsigned int, rxm->full_len, len); @@ -2040,7 +2044,17 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, if (copied < 0) goto splice_read_end; - tls_sw_advance_skb(sk, skb, copied); + if (!from_queue) { + ctx->recv_pkt = NULL; + __strp_unpause(&ctx->strp); + } + if (chunk < rxm->full_len) { + __skb_queue_head(&ctx->rx_list, skb); + rxm->offset += len; + rxm->full_len -= len; + } else { + consume_skb(skb); + } splice_read_end: release_sock(sk); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 78e08e82c08c..b0bfc78e421c 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2882,9 +2882,6 @@ static int unix_shutdown(struct socket *sock, int mode) unix_state_lock(sk); sk->sk_shutdown |= mode; - if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) && - mode == SHUTDOWN_MASK) - sk->sk_state = TCP_CLOSE; other = unix_peer(sk); if (other) sock_hold(other); diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 4f7c99dfd16c..3f82b2f1e6dd 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -731,6 +731,7 @@ static unsigned int features[] = { static struct virtio_driver virtio_vsock_driver = { .feature_table = features, .feature_table_size = ARRAY_SIZE(features), + .suppress_used_validation = true, .driver.name = KBUILD_MODNAME, .driver.owner = THIS_MODULE, .id_table = id_table, diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index b3610fdd1fee..eebd3894fe89 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -7,24 +7,23 @@ /* This struct should be in sync with struct rtnl_link_stats64 */ struct rtnl_link_stats { - __u32 rx_packets; /* total packets received */ - __u32 tx_packets; /* total packets transmitted */ - __u32 rx_bytes; /* total bytes received */ - __u32 tx_bytes; /* total bytes transmitted */ - __u32 rx_errors; /* bad packets received */ - __u32 tx_errors; /* packet transmit problems */ - __u32 rx_dropped; /* no space in linux buffers */ - __u32 tx_dropped; /* no space available in linux */ - __u32 multicast; /* multicast packets received */ + __u32 rx_packets; + __u32 tx_packets; + __u32 rx_bytes; + __u32 tx_bytes; + __u32 rx_errors; + __u32 tx_errors; + __u32 rx_dropped; + __u32 tx_dropped; + __u32 multicast; __u32 collisions; - /* detailed rx_errors: */ __u32 rx_length_errors; - __u32 rx_over_errors; /* receiver ring buff overflow */ - __u32 rx_crc_errors; /* recved pkt with crc error */ - __u32 rx_frame_errors; /* recv'd frame alignment error */ - __u32 rx_fifo_errors; /* recv'r fifo overrun */ - __u32 rx_missed_errors; /* receiver missed packet */ + __u32 rx_over_errors; + __u32 rx_crc_errors; + __u32 rx_frame_errors; + __u32 rx_fifo_errors; + __u32 rx_missed_errors; /* detailed tx_errors */ __u32 tx_aborted_errors; @@ -37,29 +36,201 @@ struct rtnl_link_stats { __u32 rx_compressed; __u32 tx_compressed; - __u32 rx_nohandler; /* dropped, no handler found */ + __u32 rx_nohandler; }; -/* The main device statistics structure */ +/** + * struct rtnl_link_stats64 - The main device statistics structure. + * + * @rx_packets: Number of good packets received by the interface. + * For hardware interfaces counts all good packets received from the device + * by the host, including packets which host had to drop at various stages + * of processing (even in the driver). + * + * @tx_packets: Number of packets successfully transmitted. + * For hardware interfaces counts packets which host was able to successfully + * hand over to the device, which does not necessarily mean that packets + * had been successfully transmitted out of the device, only that device + * acknowledged it copied them out of host memory. + * + * @rx_bytes: Number of good received bytes, corresponding to @rx_packets. + * + * For IEEE 802.3 devices should count the length of Ethernet Frames + * excluding the FCS. + * + * @tx_bytes: Number of good transmitted bytes, corresponding to @tx_packets. + * + * For IEEE 802.3 devices should count the length of Ethernet Frames + * excluding the FCS. + * + * @rx_errors: Total number of bad packets received on this network device. + * This counter must include events counted by @rx_length_errors, + * @rx_crc_errors, @rx_frame_errors and other errors not otherwise + * counted. + * + * @tx_errors: Total number of transmit problems. + * This counter must include events counter by @tx_aborted_errors, + * @tx_carrier_errors, @tx_fifo_errors, @tx_heartbeat_errors, + * @tx_window_errors and other errors not otherwise counted. + * + * @rx_dropped: Number of packets received but not processed, + * e.g. due to lack of resources or unsupported protocol. + * For hardware interfaces this counter may include packets discarded + * due to L2 address filtering but should not include packets dropped + * by the device due to buffer exhaustion which are counted separately in + * @rx_missed_errors (since procfs folds those two counters together). + * + * @tx_dropped: Number of packets dropped on their way to transmission, + * e.g. due to lack of resources. + * + * @multicast: Multicast packets received. + * For hardware interfaces this statistic is commonly calculated + * at the device level (unlike @rx_packets) and therefore may include + * packets which did not reach the host. + * + * For IEEE 802.3 devices this counter may be equivalent to: + * + * - 30.3.1.1.21 aMulticastFramesReceivedOK + * + * @collisions: Number of collisions during packet transmissions. + * + * @rx_length_errors: Number of packets dropped due to invalid length. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter should be equivalent to a sum + * of the following attributes: + * + * - 30.3.1.1.23 aInRangeLengthErrors + * - 30.3.1.1.24 aOutOfRangeLengthField + * - 30.3.1.1.25 aFrameTooLongErrors + * + * @rx_over_errors: Receiver FIFO overflow event counter. + * + * Historically the count of overflow events. Such events may be + * reported in the receive descriptors or via interrupts, and may + * not correspond one-to-one with dropped packets. + * + * The recommended interpretation for high speed interfaces is - + * number of packets dropped because they did not fit into buffers + * provided by the host, e.g. packets larger than MTU or next buffer + * in the ring was not available for a scatter transfer. + * + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * This statistics was historically used interchangeably with + * @rx_fifo_errors. + * + * This statistic corresponds to hardware events and is not commonly used + * on software devices. + * + * @rx_crc_errors: Number of packets received with a CRC error. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.6 aFrameCheckSequenceErrors + * + * @rx_frame_errors: Receiver frame alignment errors. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter should be equivalent to: + * + * - 30.3.1.1.7 aAlignmentErrors + * + * @rx_fifo_errors: Receiver FIFO error counter. + * + * Historically the count of overflow events. Those events may be + * reported in the receive descriptors or via interrupts, and may + * not correspond one-to-one with dropped packets. + * + * This statistics was used interchangeably with @rx_over_errors. + * Not recommended for use in drivers for high speed interfaces. + * + * This statistic is used on software devices, e.g. to count software + * packet queue overflow (can) or sequencing errors (GRE). + * + * @rx_missed_errors: Count of packets missed by the host. + * Folded into the "drop" counter in `/proc/net/dev`. + * + * Counts number of packets dropped by the device due to lack + * of buffer space. This usually indicates that the host interface + * is slower than the network interface, or host is not keeping up + * with the receive packet rate. + * + * This statistic corresponds to hardware events and is not used + * on software devices. + * + * @tx_aborted_errors: + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * For IEEE 802.3 devices capable of half-duplex operation this counter + * must be equivalent to: + * + * - 30.3.1.1.11 aFramesAbortedDueToXSColls + * + * High speed interfaces may use this counter as a general device + * discard counter. + * + * @tx_carrier_errors: Number of frame transmission errors due to loss + * of carrier during transmission. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.13 aCarrierSenseErrors + * + * @tx_fifo_errors: Number of frame transmission errors due to device + * FIFO underrun / underflow. This condition occurs when the device + * begins transmission of a frame but is unable to deliver the + * entire frame to the transmitter in time for transmission. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * @tx_heartbeat_errors: Number of Heartbeat / SQE Test errors for + * old half-duplex Ethernet. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices possibly equivalent to: + * + * - 30.3.2.1.4 aSQETestErrors + * + * @tx_window_errors: Number of frame transmission errors due + * to late collisions (for Ethernet - after the first 64B of transmission). + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.10 aLateCollisions + * + * @rx_compressed: Number of correctly received compressed packets. + * This counters is only meaningful for interfaces which support + * packet compression (e.g. CSLIP, PPP). + * + * @tx_compressed: Number of transmitted compressed packets. + * This counters is only meaningful for interfaces which support + * packet compression (e.g. CSLIP, PPP). + * + * @rx_nohandler: Number of packets received on the interface + * but dropped by the networking stack because the device is + * not designated to receive packets (e.g. backup link in a bond). + */ struct rtnl_link_stats64 { - __u64 rx_packets; /* total packets received */ - __u64 tx_packets; /* total packets transmitted */ - __u64 rx_bytes; /* total bytes received */ - __u64 tx_bytes; /* total bytes transmitted */ - __u64 rx_errors; /* bad packets received */ - __u64 tx_errors; /* packet transmit problems */ - __u64 rx_dropped; /* no space in linux buffers */ - __u64 tx_dropped; /* no space available in linux */ - __u64 multicast; /* multicast packets received */ + __u64 rx_packets; + __u64 tx_packets; + __u64 rx_bytes; + __u64 tx_bytes; + __u64 rx_errors; + __u64 tx_errors; + __u64 rx_dropped; + __u64 tx_dropped; + __u64 multicast; __u64 collisions; /* detailed rx_errors: */ __u64 rx_length_errors; - __u64 rx_over_errors; /* receiver ring buff overflow */ - __u64 rx_crc_errors; /* recved pkt with crc error */ - __u64 rx_frame_errors; /* recv'd frame alignment error */ - __u64 rx_fifo_errors; /* recv'r fifo overrun */ - __u64 rx_missed_errors; /* receiver missed packet */ + __u64 rx_over_errors; + __u64 rx_crc_errors; + __u64 rx_frame_errors; + __u64 rx_fifo_errors; + __u64 rx_missed_errors; /* detailed tx_errors */ __u64 tx_aborted_errors; @@ -71,8 +242,7 @@ struct rtnl_link_stats64 { /* for cslip etc */ __u64 rx_compressed; __u64 tx_compressed; - - __u64 rx_nohandler; /* dropped, no handler found */ + __u64 rx_nohandler; }; /* The struct should be in sync with struct ifmap */ @@ -170,12 +340,29 @@ enum { IFLA_PROP_LIST, IFLA_ALT_IFNAME, /* Alternative ifname */ IFLA_PERM_ADDRESS, + IFLA_PROTO_DOWN_REASON, + + /* device (sysfs) name as parent, used instead + * of IFLA_LINK where there's no parent netdev + */ + IFLA_PARENT_DEV_NAME, + IFLA_PARENT_DEV_BUS_NAME, + __IFLA_MAX }; #define IFLA_MAX (__IFLA_MAX - 1) +enum { + IFLA_PROTO_DOWN_REASON_UNSPEC, + IFLA_PROTO_DOWN_REASON_MASK, /* u32, mask for reason bits */ + IFLA_PROTO_DOWN_REASON_VALUE, /* u32, reason bit value */ + + __IFLA_PROTO_DOWN_REASON_CNT, + IFLA_PROTO_DOWN_REASON_MAX = __IFLA_PROTO_DOWN_REASON_CNT - 1 +}; + /* backwards compatibility for userspace */ #ifndef __KERNEL__ #define IFLA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg)))) @@ -293,6 +480,7 @@ enum { IFLA_BR_MCAST_MLD_VERSION, IFLA_BR_VLAN_STATS_PER_PORT, IFLA_BR_MULTI_BOOLOPT, + IFLA_BR_MCAST_QUERIER_STATE, __IFLA_BR_MAX, }; @@ -346,6 +534,8 @@ enum { IFLA_BRPORT_BACKUP_PORT, IFLA_BRPORT_MRP_RING_OPEN, IFLA_BRPORT_MRP_IN_OPEN, + IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, + IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) @@ -433,6 +623,7 @@ enum macvlan_macaddr_mode { }; #define MACVLAN_FLAG_NOPROMISC 1 +#define MACVLAN_FLAG_NODST 2 /* skip dst macvlan if matching src macvlan */ /* VRF section */ enum { @@ -597,6 +788,18 @@ enum ifla_geneve_df { GENEVE_DF_MAX = __GENEVE_DF_END - 1, }; +/* Bareudp section */ +enum { + IFLA_BAREUDP_UNSPEC, + IFLA_BAREUDP_PORT, + IFLA_BAREUDP_ETHERTYPE, + IFLA_BAREUDP_SRCPORT_MIN, + IFLA_BAREUDP_MULTIPROTO_MODE, + __IFLA_BAREUDP_MAX +}; + +#define IFLA_BAREUDP_MAX (__IFLA_BAREUDP_MAX - 1) + /* PPP section */ enum { IFLA_PPP_UNSPEC, @@ -899,7 +1102,14 @@ enum { #define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1) -/* HSR section */ +/* HSR/PRP section, both uses same interface */ + +/* Different redundancy protocols for hsr device */ +enum { + HSR_PROTOCOL_HSR, + HSR_PROTOCOL_PRP, + HSR_PROTOCOL_MAX, +}; enum { IFLA_HSR_UNSPEC, @@ -909,6 +1119,9 @@ enum { IFLA_HSR_SUPERVISION_ADDR, /* Supervision frame multicast addr */ IFLA_HSR_SEQ_NR, IFLA_HSR_VERSION, /* HSR version */ + IFLA_HSR_PROTOCOL, /* Indicate different protocol than + * HSR. For example PRP. + */ __IFLA_HSR_MAX, }; @@ -1033,6 +1246,8 @@ enum { #define RMNET_FLAGS_INGRESS_MAP_COMMANDS (1U << 1) #define RMNET_FLAGS_INGRESS_MAP_CKSUMV4 (1U << 2) #define RMNET_FLAGS_EGRESS_MAP_CKSUMV4 (1U << 3) +#define RMNET_FLAGS_INGRESS_MAP_CKSUMV5 (1U << 4) +#define RMNET_FLAGS_EGRESS_MAP_CKSUMV5 (1U << 5) enum { IFLA_RMNET_UNSPEC, @@ -1048,4 +1263,14 @@ struct ifla_rmnet_flags { __u32 mask; }; +/* MCTP section */ + +enum { + IFLA_MCTP_UNSPEC, + IFLA_MCTP_NET, + __IFLA_MCTP_MAX, +}; + +#define IFLA_MCTP_MAX (__IFLA_MCTP_MAX - 1) + #endif /* _UAPI_LINUX_IF_LINK_H */ diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 7615f29831eb..9897fa9ab953 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -34,6 +34,7 @@ TEST_PROGS += srv6_end_dt46_l3vpn_test.sh TEST_PROGS += srv6_end_dt4_l3vpn_test.sh TEST_PROGS += srv6_end_dt6_l3vpn_test.sh TEST_PROGS += vrf_strict_mode_test.sh +TEST_PROGS += arp_ndisc_evict_nocarrier.sh TEST_PROGS_EXTENDED := in_netns.sh setup_loopback.sh setup_veth.sh TEST_PROGS_EXTENDED += toeplitz_client.sh toeplitz.sh TEST_GEN_FILES = socket nettest diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index b5a69ad191b0..d444ee6aa3cb 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -629,6 +629,66 @@ ipv6_fcnal() log_test $? 0 "Nexthops removed on admin down" } +ipv6_grp_refs() +{ + if [ ! -x "$(command -v mausezahn)" ]; then + echo "SKIP: Could not run test; need mausezahn tool" + return + fi + + run_cmd "$IP link set dev veth1 up" + run_cmd "$IP link add veth1.10 link veth1 up type vlan id 10" + run_cmd "$IP link add veth1.20 link veth1 up type vlan id 20" + run_cmd "$IP -6 addr add 2001:db8:91::1/64 dev veth1.10" + run_cmd "$IP -6 addr add 2001:db8:92::1/64 dev veth1.20" + run_cmd "$IP -6 neigh add 2001:db8:91::2 lladdr 00:11:22:33:44:55 dev veth1.10" + run_cmd "$IP -6 neigh add 2001:db8:92::2 lladdr 00:11:22:33:44:55 dev veth1.20" + run_cmd "$IP nexthop add id 100 via 2001:db8:91::2 dev veth1.10" + run_cmd "$IP nexthop add id 101 via 2001:db8:92::2 dev veth1.20" + run_cmd "$IP nexthop add id 102 group 100" + run_cmd "$IP route add 2001:db8:101::1/128 nhid 102" + + # create per-cpu dsts through nh 100 + run_cmd "ip netns exec me mausezahn -6 veth1.10 -B 2001:db8:101::1 -A 2001:db8:91::1 -c 5 -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1" + + # remove nh 100 from the group to delete the route potentially leaving + # a stale per-cpu dst which holds a reference to the nexthop's net + # device and to the IPv6 route + run_cmd "$IP nexthop replace id 102 group 101" + run_cmd "$IP route del 2001:db8:101::1/128" + + # add both nexthops to the group so a reference is taken on them + run_cmd "$IP nexthop replace id 102 group 100/101" + + # if the bug described in commit "net: nexthop: release IPv6 per-cpu + # dsts when replacing a nexthop group" exists at this point we have + # an unlinked IPv6 route (but not freed due to stale dst) with a + # reference over the group so we delete the group which will again + # only unlink it due to the route reference + run_cmd "$IP nexthop del id 102" + + # delete the nexthop with stale dst, since we have an unlinked + # group with a ref to it and an unlinked IPv6 route with ref to the + # group, the nh will only be unlinked and not freed so the stale dst + # remains forever and we get a net device refcount imbalance + run_cmd "$IP nexthop del id 100" + + # if a reference was lost this command will hang because the net device + # cannot be removed + timeout -s KILL 5 ip netns exec me ip link del veth1.10 >/dev/null 2>&1 + + # we can't cleanup if the command is hung trying to delete the netdev + if [ $? -eq 137 ]; then + return 1 + fi + + # cleanup + run_cmd "$IP link del veth1.20" + run_cmd "$IP nexthop flush" + + return 0 +} + ipv6_grp_fcnal() { local rc @@ -734,6 +794,9 @@ ipv6_grp_fcnal() run_cmd "$IP nexthop add id 108 group 31/24" log_test $? 2 "Nexthop group can not have a blackhole and another nexthop" + + ipv6_grp_refs + log_test $? 0 "Nexthop group replace refcounts" } ipv6_res_grp_fcnal() diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index e61fc4c32ba2..8a22db0cca49 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -78,26 +78,21 @@ static void memrnd(void *s, size_t n) *byte++ = rand(); } -FIXTURE(tls_basic) -{ - int fd, cfd; - bool notls; -}; - -FIXTURE_SETUP(tls_basic) +static void ulp_sock_pair(struct __test_metadata *_metadata, + int *fd, int *cfd, bool *notls) { struct sockaddr_in addr; socklen_t len; int sfd, ret; - self->notls = false; + *notls = false; len = sizeof(addr); addr.sin_family = AF_INET; addr.sin_addr.s_addr = htonl(INADDR_ANY); addr.sin_port = 0; - self->fd = socket(AF_INET, SOCK_STREAM, 0); + *fd = socket(AF_INET, SOCK_STREAM, 0); sfd = socket(AF_INET, SOCK_STREAM, 0); ret = bind(sfd, &addr, sizeof(addr)); @@ -108,26 +103,96 @@ FIXTURE_SETUP(tls_basic) ret = getsockname(sfd, &addr, &len); ASSERT_EQ(ret, 0); - ret = connect(self->fd, &addr, sizeof(addr)); + ret = connect(*fd, &addr, sizeof(addr)); ASSERT_EQ(ret, 0); - self->cfd = accept(sfd, &addr, &len); - ASSERT_GE(self->cfd, 0); + *cfd = accept(sfd, &addr, &len); + ASSERT_GE(*cfd, 0); close(sfd); - ret = setsockopt(self->fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + ret = setsockopt(*fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); if (ret != 0) { ASSERT_EQ(errno, ENOENT); - self->notls = true; + *notls = true; printf("Failure setting TCP_ULP, testing without tls\n"); return; } - ret = setsockopt(self->cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + ret = setsockopt(*cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); ASSERT_EQ(ret, 0); } +/* Produce a basic cmsg */ +static int tls_send_cmsg(int fd, unsigned char record_type, + void *data, size_t len, int flags) +{ + char cbuf[CMSG_SPACE(sizeof(char))]; + int cmsg_len = sizeof(char); + struct cmsghdr *cmsg; + struct msghdr msg; + struct iovec vec; + + vec.iov_base = data; + vec.iov_len = len; + memset(&msg, 0, sizeof(struct msghdr)); + msg.msg_iov = &vec; + msg.msg_iovlen = 1; + msg.msg_control = cbuf; + msg.msg_controllen = sizeof(cbuf); + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_TLS; + /* test sending non-record types. */ + cmsg->cmsg_type = TLS_SET_RECORD_TYPE; + cmsg->cmsg_len = CMSG_LEN(cmsg_len); + *CMSG_DATA(cmsg) = record_type; + msg.msg_controllen = cmsg->cmsg_len; + + return sendmsg(fd, &msg, flags); +} + +static int tls_recv_cmsg(struct __test_metadata *_metadata, + int fd, unsigned char record_type, + void *data, size_t len, int flags) +{ + char cbuf[CMSG_SPACE(sizeof(char))]; + struct cmsghdr *cmsg; + unsigned char ctype; + struct msghdr msg; + struct iovec vec; + int n; + + vec.iov_base = data; + vec.iov_len = len; + memset(&msg, 0, sizeof(struct msghdr)); + msg.msg_iov = &vec; + msg.msg_iovlen = 1; + msg.msg_control = cbuf; + msg.msg_controllen = sizeof(cbuf); + + n = recvmsg(fd, &msg, flags); + + cmsg = CMSG_FIRSTHDR(&msg); + EXPECT_NE(cmsg, NULL); + EXPECT_EQ(cmsg->cmsg_level, SOL_TLS); + EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE); + ctype = *((unsigned char *)CMSG_DATA(cmsg)); + EXPECT_EQ(ctype, record_type); + + return n; +} + +FIXTURE(tls_basic) +{ + int fd, cfd; + bool notls; +}; + +FIXTURE_SETUP(tls_basic) +{ + ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls); +} + FIXTURE_TEARDOWN(tls_basic) { close(self->fd); @@ -199,60 +264,21 @@ FIXTURE_VARIANT_ADD(tls, 13_sm4_ccm) FIXTURE_SETUP(tls) { struct tls_crypto_info_keys tls12; - struct sockaddr_in addr; - socklen_t len; - int sfd, ret; - - self->notls = false; - len = sizeof(addr); + int ret; tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12); - addr.sin_family = AF_INET; - addr.sin_addr.s_addr = htonl(INADDR_ANY); - addr.sin_port = 0; + ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls); - self->fd = socket(AF_INET, SOCK_STREAM, 0); - sfd = socket(AF_INET, SOCK_STREAM, 0); - - ret = bind(sfd, &addr, sizeof(addr)); - ASSERT_EQ(ret, 0); - ret = listen(sfd, 10); - ASSERT_EQ(ret, 0); + if (self->notls) + return; - ret = getsockname(sfd, &addr, &len); + ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len); ASSERT_EQ(ret, 0); - ret = connect(self->fd, &addr, sizeof(addr)); + ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len); ASSERT_EQ(ret, 0); - - ret = setsockopt(self->fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); - if (ret != 0) { - self->notls = true; - printf("Failure setting TCP_ULP, testing without tls\n"); - } - - if (!self->notls) { - ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, - tls12.len); - ASSERT_EQ(ret, 0); - } - - self->cfd = accept(sfd, &addr, &len); - ASSERT_GE(self->cfd, 0); - - if (!self->notls) { - ret = setsockopt(self->cfd, IPPROTO_TCP, TCP_ULP, "tls", - sizeof("tls")); - ASSERT_EQ(ret, 0); - - ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, - tls12.len); - ASSERT_EQ(ret, 0); - } - - close(sfd); } FIXTURE_TEARDOWN(tls) @@ -613,6 +639,95 @@ TEST_F(tls, splice_to_pipe) EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); } +TEST_F(tls, splice_cmsg_to_pipe) +{ + char *test_str = "test_read"; + char record_type = 100; + int send_len = 10; + char buf[10]; + int p[2]; + + ASSERT_GE(pipe(p), 0); + EXPECT_EQ(tls_send_cmsg(self->fd, 100, test_str, send_len, 0), 10); + EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, send_len, 0), -1); + EXPECT_EQ(errno, EINVAL); + EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1); + EXPECT_EQ(errno, EIO); + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type, + buf, sizeof(buf), MSG_WAITALL), + send_len); + EXPECT_EQ(memcmp(test_str, buf, send_len), 0); +} + +TEST_F(tls, splice_dec_cmsg_to_pipe) +{ + char *test_str = "test_read"; + char record_type = 100; + int send_len = 10; + char buf[10]; + int p[2]; + + ASSERT_GE(pipe(p), 0); + EXPECT_EQ(tls_send_cmsg(self->fd, 100, test_str, send_len, 0), 10); + EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1); + EXPECT_EQ(errno, EIO); + EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, send_len, 0), -1); + EXPECT_EQ(errno, EINVAL); + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type, + buf, sizeof(buf), MSG_WAITALL), + send_len); + EXPECT_EQ(memcmp(test_str, buf, send_len), 0); +} + +TEST_F(tls, recv_and_splice) +{ + int send_len = TLS_PAYLOAD_MAX_LEN; + char mem_send[TLS_PAYLOAD_MAX_LEN]; + char mem_recv[TLS_PAYLOAD_MAX_LEN]; + int half = send_len / 2; + int p[2]; + + ASSERT_GE(pipe(p), 0); + EXPECT_EQ(send(self->fd, mem_send, send_len, 0), send_len); + /* Recv hald of the record, splice the other half */ + EXPECT_EQ(recv(self->cfd, mem_recv, half, MSG_WAITALL), half); + EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, half, SPLICE_F_NONBLOCK), + half); + EXPECT_EQ(read(p[0], &mem_recv[half], half), half); + EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); +} + +TEST_F(tls, peek_and_splice) +{ + int send_len = TLS_PAYLOAD_MAX_LEN; + char mem_send[TLS_PAYLOAD_MAX_LEN]; + char mem_recv[TLS_PAYLOAD_MAX_LEN]; + int chunk = TLS_PAYLOAD_MAX_LEN / 4; + int n, i, p[2]; + + memrnd(mem_send, sizeof(mem_send)); + + ASSERT_GE(pipe(p), 0); + for (i = 0; i < 4; i++) + EXPECT_EQ(send(self->fd, &mem_send[chunk * i], chunk, 0), + chunk); + + EXPECT_EQ(recv(self->cfd, mem_recv, chunk * 5 / 2, + MSG_WAITALL | MSG_PEEK), + chunk * 5 / 2); + EXPECT_EQ(memcmp(mem_send, mem_recv, chunk * 5 / 2), 0); + + n = 0; + while (n < send_len) { + i = splice(self->cfd, NULL, p[1], NULL, send_len - n, 0); + EXPECT_GT(i, 0); + n += i; + } + EXPECT_EQ(n, send_len); + EXPECT_EQ(read(p[0], mem_recv, send_len), send_len); + EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); +} + TEST_F(tls, recvmsg_single) { char const *test_str = "test_recvmsg_single"; @@ -1193,60 +1308,30 @@ TEST_F(tls, mutliproc_sendpage_writers) TEST_F(tls, control_msg) { - if (self->notls) - return; - - char cbuf[CMSG_SPACE(sizeof(char))]; - char const *test_str = "test_read"; - int cmsg_len = sizeof(char); + char *test_str = "test_read"; char record_type = 100; - struct cmsghdr *cmsg; - struct msghdr msg; int send_len = 10; - struct iovec vec; char buf[10]; - vec.iov_base = (char *)test_str; - vec.iov_len = 10; - memset(&msg, 0, sizeof(struct msghdr)); - msg.msg_iov = &vec; - msg.msg_iovlen = 1; - msg.msg_control = cbuf; - msg.msg_controllen = sizeof(cbuf); - cmsg = CMSG_FIRSTHDR(&msg); - cmsg->cmsg_level = SOL_TLS; - /* test sending non-record types. */ - cmsg->cmsg_type = TLS_SET_RECORD_TYPE; - cmsg->cmsg_len = CMSG_LEN(cmsg_len); - *CMSG_DATA(cmsg) = record_type; - msg.msg_controllen = cmsg->cmsg_len; + if (self->notls) + SKIP(return, "no TLS support"); - EXPECT_EQ(sendmsg(self->fd, &msg, 0), send_len); + EXPECT_EQ(tls_send_cmsg(self->fd, record_type, test_str, send_len, 0), + send_len); /* Should fail because we didn't provide a control message */ EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1); - vec.iov_base = buf; - EXPECT_EQ(recvmsg(self->cfd, &msg, MSG_WAITALL | MSG_PEEK), send_len); - - cmsg = CMSG_FIRSTHDR(&msg); - EXPECT_NE(cmsg, NULL); - EXPECT_EQ(cmsg->cmsg_level, SOL_TLS); - EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE); - record_type = *((unsigned char *)CMSG_DATA(cmsg)); - EXPECT_EQ(record_type, 100); + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type, + buf, sizeof(buf), MSG_WAITALL | MSG_PEEK), + send_len); EXPECT_EQ(memcmp(buf, test_str, send_len), 0); /* Recv the message again without MSG_PEEK */ - record_type = 0; memset(buf, 0, sizeof(buf)); - EXPECT_EQ(recvmsg(self->cfd, &msg, MSG_WAITALL), send_len); - cmsg = CMSG_FIRSTHDR(&msg); - EXPECT_NE(cmsg, NULL); - EXPECT_EQ(cmsg->cmsg_level, SOL_TLS); - EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE); - record_type = *((unsigned char *)CMSG_DATA(cmsg)); - EXPECT_EQ(record_type, 100); + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type, + buf, sizeof(buf), MSG_WAITALL), + send_len); EXPECT_EQ(memcmp(buf, test_str, send_len), 0); } @@ -1301,6 +1386,160 @@ TEST_F(tls, shutdown_reuse) EXPECT_EQ(errno, EISCONN); } +FIXTURE(tls_err) +{ + int fd, cfd; + int fd2, cfd2; + bool notls; +}; + +FIXTURE_VARIANT(tls_err) +{ + uint16_t tls_version; +}; + +FIXTURE_VARIANT_ADD(tls_err, 12_aes_gcm) +{ + .tls_version = TLS_1_2_VERSION, +}; + +FIXTURE_VARIANT_ADD(tls_err, 13_aes_gcm) +{ + .tls_version = TLS_1_3_VERSION, +}; + +FIXTURE_SETUP(tls_err) +{ + struct tls_crypto_info_keys tls12; + int ret; + + tls_crypto_info_init(variant->tls_version, TLS_CIPHER_AES_GCM_128, + &tls12); + + ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls); + ulp_sock_pair(_metadata, &self->fd2, &self->cfd2, &self->notls); + if (self->notls) + return; + + ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(self->cfd2, SOL_TLS, TLS_RX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); +} + +FIXTURE_TEARDOWN(tls_err) +{ + close(self->fd); + close(self->cfd); + close(self->fd2); + close(self->cfd2); +} + +TEST_F(tls_err, bad_rec) +{ + char buf[64]; + + if (self->notls) + SKIP(return, "no TLS support"); + + memset(buf, 0x55, sizeof(buf)); + EXPECT_EQ(send(self->fd2, buf, sizeof(buf), 0), sizeof(buf)); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EMSGSIZE); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), MSG_DONTWAIT), -1); + EXPECT_EQ(errno, EAGAIN); +} + +TEST_F(tls_err, bad_auth) +{ + char buf[128]; + int n; + + if (self->notls) + SKIP(return, "no TLS support"); + + memrnd(buf, sizeof(buf) / 2); + EXPECT_EQ(send(self->fd, buf, sizeof(buf) / 2, 0), sizeof(buf) / 2); + n = recv(self->cfd, buf, sizeof(buf), 0); + EXPECT_GT(n, sizeof(buf) / 2); + + buf[n - 1]++; + + EXPECT_EQ(send(self->fd2, buf, n, 0), n); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); +} + +TEST_F(tls_err, bad_in_large_read) +{ + char txt[3][64]; + char cip[3][128]; + char buf[3 * 128]; + int i, n; + + if (self->notls) + SKIP(return, "no TLS support"); + + /* Put 3 records in the sockets */ + for (i = 0; i < 3; i++) { + memrnd(txt[i], sizeof(txt[i])); + EXPECT_EQ(send(self->fd, txt[i], sizeof(txt[i]), 0), + sizeof(txt[i])); + n = recv(self->cfd, cip[i], sizeof(cip[i]), 0); + EXPECT_GT(n, sizeof(txt[i])); + /* Break the third message */ + if (i == 2) + cip[2][n - 1]++; + EXPECT_EQ(send(self->fd2, cip[i], n, 0), n); + } + + /* We should be able to receive the first two messages */ + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), sizeof(txt[0]) * 2); + EXPECT_EQ(memcmp(buf, txt[0], sizeof(txt[0])), 0); + EXPECT_EQ(memcmp(buf + sizeof(txt[0]), txt[1], sizeof(txt[1])), 0); + /* Third mesasge is bad */ + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); +} + +TEST_F(tls_err, bad_cmsg) +{ + char *test_str = "test_read"; + int send_len = 10; + char cip[128]; + char buf[128]; + char txt[64]; + int n; + + if (self->notls) + SKIP(return, "no TLS support"); + + /* Queue up one data record */ + memrnd(txt, sizeof(txt)); + EXPECT_EQ(send(self->fd, txt, sizeof(txt), 0), sizeof(txt)); + n = recv(self->cfd, cip, sizeof(cip), 0); + EXPECT_GT(n, sizeof(txt)); + EXPECT_EQ(send(self->fd2, cip, n, 0), n); + + EXPECT_EQ(tls_send_cmsg(self->fd, 100, test_str, send_len, 0), 10); + n = recv(self->cfd, cip, sizeof(cip), 0); + cip[n - 1]++; /* Break it */ + EXPECT_GT(n, send_len); + EXPECT_EQ(send(self->fd2, cip, n, 0), n); + + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), sizeof(txt)); + EXPECT_EQ(memcmp(buf, txt, sizeof(txt)), 0); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); +} + TEST(non_established) { struct tls12_crypto_info_aes_gcm_256 tls12; struct sockaddr_in addr; @@ -1355,64 +1594,82 @@ TEST(non_established) { TEST(keysizes) { struct tls12_crypto_info_aes_gcm_256 tls12; - struct sockaddr_in addr; - int sfd, ret, fd, cfd; - socklen_t len; + int ret, fd, cfd; bool notls; - notls = false; - len = sizeof(addr); - memset(&tls12, 0, sizeof(tls12)); tls12.info.version = TLS_1_2_VERSION; tls12.info.cipher_type = TLS_CIPHER_AES_GCM_256; - addr.sin_family = AF_INET; - addr.sin_addr.s_addr = htonl(INADDR_ANY); - addr.sin_port = 0; + ulp_sock_pair(_metadata, &fd, &cfd, ¬ls); - fd = socket(AF_INET, SOCK_STREAM, 0); - sfd = socket(AF_INET, SOCK_STREAM, 0); + if (!notls) { + ret = setsockopt(fd, SOL_TLS, TLS_TX, &tls12, + sizeof(tls12)); + EXPECT_EQ(ret, 0); + + ret = setsockopt(cfd, SOL_TLS, TLS_RX, &tls12, + sizeof(tls12)); + EXPECT_EQ(ret, 0); + } + + close(fd); + close(cfd); +} + +TEST(tls_v6ops) { + struct tls_crypto_info_keys tls12; + struct sockaddr_in6 addr, addr2; + int sfd, ret, fd; + socklen_t len, len2; + + tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_128, &tls12); + + addr.sin6_family = AF_INET6; + addr.sin6_addr = in6addr_any; + addr.sin6_port = 0; + + fd = socket(AF_INET6, SOCK_STREAM, 0); + sfd = socket(AF_INET6, SOCK_STREAM, 0); ret = bind(sfd, &addr, sizeof(addr)); ASSERT_EQ(ret, 0); ret = listen(sfd, 10); ASSERT_EQ(ret, 0); + len = sizeof(addr); ret = getsockname(sfd, &addr, &len); ASSERT_EQ(ret, 0); ret = connect(fd, &addr, sizeof(addr)); ASSERT_EQ(ret, 0); + len = sizeof(addr); + ret = getsockname(fd, &addr, &len); + ASSERT_EQ(ret, 0); + ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); - if (ret != 0) { - notls = true; - printf("Failure setting TCP_ULP, testing without tls\n"); + if (ret) { + ASSERT_EQ(errno, ENOENT); + SKIP(return, "no TLS support"); } + ASSERT_EQ(ret, 0); - if (!notls) { - ret = setsockopt(fd, SOL_TLS, TLS_TX, &tls12, - sizeof(tls12)); - EXPECT_EQ(ret, 0); - } + ret = setsockopt(fd, SOL_TLS, TLS_TX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); - cfd = accept(sfd, &addr, &len); - ASSERT_GE(cfd, 0); + ret = setsockopt(fd, SOL_TLS, TLS_RX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); - if (!notls) { - ret = setsockopt(cfd, IPPROTO_TCP, TCP_ULP, "tls", - sizeof("tls")); - EXPECT_EQ(ret, 0); + len2 = sizeof(addr2); + ret = getsockname(fd, &addr2, &len2); + ASSERT_EQ(ret, 0); - ret = setsockopt(cfd, SOL_TLS, TLS_RX, &tls12, - sizeof(tls12)); - EXPECT_EQ(ret, 0); - } + EXPECT_EQ(len2, len); + EXPECT_EQ(memcmp(&addr, &addr2, len), 0); - close(sfd); close(fd); - close(cfd); + close(sfd); } TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index 8748199ac109..ffca314897c4 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -5,7 +5,8 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \ conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \ nft_concat_range.sh nft_conntrack_helper.sh \ nft_queue.sh nft_meta.sh nf_nat_edemux.sh \ - ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh + ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh \ + conntrack_vrf.sh LDLIBS = -lmnl TEST_GEN_FILES = nf-queue diff --git a/tools/testing/selftests/netfilter/conntrack_vrf.sh b/tools/testing/selftests/netfilter/conntrack_vrf.sh new file mode 100755 index 000000000000..91f3ef0f1192 --- /dev/null +++ b/tools/testing/selftests/netfilter/conntrack_vrf.sh @@ -0,0 +1,219 @@ +#!/bin/sh + +# This script demonstrates interaction of conntrack and vrf. +# The vrf driver calls the netfilter hooks again, with oif/iif +# pointing at the VRF device. +# +# For ingress, this means first iteration has iifname of lower/real +# device. In this script, thats veth0. +# Second iteration is iifname set to vrf device, tvrf in this script. +# +# For egress, this is reversed: first iteration has the vrf device, +# second iteration is done with the lower/real/veth0 device. +# +# test_ct_zone_in demonstrates unexpected change of nftables +# behavior # caused by commit 09e856d54bda5f28 "vrf: Reset skb conntrack +# connection on VRF rcv" +# +# It was possible to assign conntrack zone to a packet (or mark it for +# `notracking`) in the prerouting chain before conntrack, based on real iif. +# +# After the change, the zone assignment is lost and the zone is assigned based +# on the VRF master interface (in case such a rule exists). +# assignment is lost. Instead, assignment based on the `iif` matching +# Thus it is impossible to distinguish packets based on the original +# interface. +# +# test_masquerade_vrf and test_masquerade_veth0 demonstrate the problem +# that was supposed to be fixed by the commit mentioned above to make sure +# that any fix to test case 1 won't break masquerade again. + +ksft_skip=4 + +IP0=172.30.30.1 +IP1=172.30.30.2 +PFXL=30 +ret=0 + +sfx=$(mktemp -u "XXXXXXXX") +ns0="ns0-$sfx" +ns1="ns1-$sfx" + +cleanup() +{ + ip netns pids $ns0 | xargs kill 2>/dev/null + ip netns pids $ns1 | xargs kill 2>/dev/null + + ip netns del $ns0 $ns1 +} + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +ip netns add "$ns0" +if [ $? -ne 0 ];then + echo "SKIP: Could not create net namespace $ns0" + exit $ksft_skip +fi +ip netns add "$ns1" + +trap cleanup EXIT + +ip netns exec $ns0 sysctl -q -w net.ipv4.conf.default.rp_filter=0 +ip netns exec $ns0 sysctl -q -w net.ipv4.conf.all.rp_filter=0 +ip netns exec $ns0 sysctl -q -w net.ipv4.conf.all.rp_filter=0 + +ip link add veth0 netns "$ns0" type veth peer name veth0 netns "$ns1" > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not add veth device" + exit $ksft_skip +fi + +ip -net $ns0 li add tvrf type vrf table 9876 +if [ $? -ne 0 ];then + echo "SKIP: Could not add vrf device" + exit $ksft_skip +fi + +ip -net $ns0 li set lo up + +ip -net $ns0 li set veth0 master tvrf +ip -net $ns0 li set tvrf up +ip -net $ns0 li set veth0 up +ip -net $ns1 li set veth0 up + +ip -net $ns0 addr add $IP0/$PFXL dev veth0 +ip -net $ns1 addr add $IP1/$PFXL dev veth0 + +ip netns exec $ns1 iperf3 -s > /dev/null 2>&1& +if [ $? -ne 0 ];then + echo "SKIP: Could not start iperf3" + exit $ksft_skip +fi + +# test vrf ingress handling. +# The incoming connection should be placed in conntrack zone 1, +# as decided by the first iteration of the ruleset. +test_ct_zone_in() +{ +ip netns exec $ns0 nft -f - <<EOF +table testct { + chain rawpre { + type filter hook prerouting priority raw; + + iif { veth0, tvrf } counter meta nftrace set 1 + iif veth0 counter ct zone set 1 counter return + iif tvrf counter ct zone set 2 counter return + ip protocol icmp counter + notrack counter + } + + chain rawout { + type filter hook output priority raw; + + oif veth0 counter ct zone set 1 counter return + oif tvrf counter ct zone set 2 counter return + notrack counter + } +} +EOF + ip netns exec $ns1 ping -W 1 -c 1 -I veth0 $IP0 > /dev/null + + # should be in zone 1, not zone 2 + count=$(ip netns exec $ns0 conntrack -L -s $IP1 -d $IP0 -p icmp --zone 1 2>/dev/null | wc -l) + if [ $count -eq 1 ]; then + echo "PASS: entry found in conntrack zone 1" + else + echo "FAIL: entry not found in conntrack zone 1" + count=$(ip netns exec $ns0 conntrack -L -s $IP1 -d $IP0 -p icmp --zone 2 2> /dev/null | wc -l) + if [ $count -eq 1 ]; then + echo "FAIL: entry found in zone 2 instead" + else + echo "FAIL: entry not in zone 1 or 2, dumping table" + ip netns exec $ns0 conntrack -L + ip netns exec $ns0 nft list ruleset + fi + fi +} + +# add masq rule that gets evaluated w. outif set to vrf device. +# This tests the first iteration of the packet through conntrack, +# oifname is the vrf device. +test_masquerade_vrf() +{ + ip netns exec $ns0 conntrack -F 2>/dev/null + +ip netns exec $ns0 nft -f - <<EOF +flush ruleset +table ip nat { + chain postrouting { + type nat hook postrouting priority 0; + # NB: masquerade should always be combined with 'oif(name) bla', + # lack of this is intentional here, we want to exercise double-snat. + ip saddr 172.30.30.0/30 counter masquerade random + } +} +EOF + ip netns exec $ns0 ip vrf exec tvrf iperf3 -t 1 -c $IP1 >/dev/null + if [ $? -ne 0 ]; then + echo "FAIL: iperf3 connect failure with masquerade + sport rewrite on vrf device" + ret=1 + return + fi + + # must also check that nat table was evaluated on second (lower device) iteration. + ip netns exec $ns0 nft list table ip nat |grep -q 'counter packets 2' + if [ $? -eq 0 ]; then + echo "PASS: iperf3 connect with masquerade + sport rewrite on vrf device" + else + echo "FAIL: vrf masq rule has unexpected counter value" + ret=1 + fi +} + +# add masq rule that gets evaluated w. outif set to veth device. +# This tests the 2nd iteration of the packet through conntrack, +# oifname is the lower device (veth0 in this case). +test_masquerade_veth() +{ + ip netns exec $ns0 conntrack -F 2>/dev/null +ip netns exec $ns0 nft -f - <<EOF +flush ruleset +table ip nat { + chain postrouting { + type nat hook postrouting priority 0; + meta oif veth0 ip saddr 172.30.30.0/30 counter masquerade random + } +} +EOF + ip netns exec $ns0 ip vrf exec tvrf iperf3 -t 1 -c $IP1 > /dev/null + if [ $? -ne 0 ]; then + echo "FAIL: iperf3 connect failure with masquerade + sport rewrite on veth device" + ret=1 + return + fi + + # must also check that nat table was evaluated on second (lower device) iteration. + ip netns exec $ns0 nft list table ip nat |grep -q 'counter packets 2' + if [ $? -eq 0 ]; then + echo "PASS: iperf3 connect with masquerade + sport rewrite on veth device" + else + echo "FAIL: vrf masq rule has unexpected counter value" + ret=1 + fi +} + +test_ct_zone_in +test_masquerade_vrf +test_masquerade_veth + +exit $ret diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index da1c1e4b6c86..d88867d2fed7 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -759,19 +759,21 @@ test_port_shadow() local result="" local logmsg="" - echo ROUTER | ip netns exec "$ns0" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 & - nc_r=$! + # make shadow entry, from client (ns2), going to (ns1), port 41404, sport 1405. + echo "fake-entry" | ip netns exec "$ns2" timeout 1 socat -u STDIN UDP:"$daddrc":41404,sourceport=1405 - echo CLIENT | ip netns exec "$ns2" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 & - nc_c=$! + echo ROUTER | ip netns exec "$ns0" timeout 5 socat -u STDIN UDP4-LISTEN:1405 & + sc_r=$! - # make shadow entry, from client (ns2), going to (ns1), port 41404, sport 1405. - echo "fake-entry" | ip netns exec "$ns2" nc -w 1 -p 1405 -u "$daddrc" 41404 > /dev/null + echo CLIENT | ip netns exec "$ns2" timeout 5 socat -u STDIN UDP4-LISTEN:1405,reuseport & + sc_c=$! + + sleep 0.3 # ns1 tries to connect to ns0:1405. With default settings this should connect # to client, it matches the conntrack entry created above. - result=$(echo "" | ip netns exec "$ns1" nc -w 1 -p 41404 -u "$daddrs" 1405) + result=$(echo "data" | ip netns exec "$ns1" timeout 1 socat - UDP:"$daddrs":1405,sourceport=41404) if [ "$result" = "$expect" ] ;then echo "PASS: portshadow test $test: got reply from ${expect}${logmsg}" @@ -780,7 +782,7 @@ test_port_shadow() ret=1 fi - kill $nc_r $nc_c 2>/dev/null + kill $sc_r $sc_c 2>/dev/null # flush udp entries for next test round, if any ip netns exec "$ns0" conntrack -F >/dev/null 2>&1 @@ -816,11 +818,10 @@ table $family raw { chain prerouting { type filter hook prerouting priority -300; policy accept; meta iif veth0 udp dport 1405 notrack - udp dport 1405 notrack } chain output { type filter hook output priority -300; policy accept; - udp sport 1405 notrack + meta oif veth0 udp sport 1405 notrack } } EOF @@ -851,6 +852,18 @@ test_port_shadowing() { local family="ip" + conntrack -h >/dev/null 2>&1 + if [ $? -ne 0 ];then + echo "SKIP: Could not run nat port shadowing test without conntrack tool" + return + fi + + socat -h > /dev/null 2>&1 + if [ $? -ne 0 ];then + echo "SKIP: Could not run nat port shadowing test without socat tool" + return + fi + ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null diff --git a/tools/testing/selftests/netfilter/nft_queue.sh b/tools/testing/selftests/netfilter/nft_queue.sh index 3d202b90b33d..7d27f1f3bc01 100755 --- a/tools/testing/selftests/netfilter/nft_queue.sh +++ b/tools/testing/selftests/netfilter/nft_queue.sh @@ -16,6 +16,10 @@ timeout=4 cleanup() { + ip netns pids ${ns1} | xargs kill 2>/dev/null + ip netns pids ${ns2} | xargs kill 2>/dev/null + ip netns pids ${nsrouter} | xargs kill 2>/dev/null + ip netns del ${ns1} ip netns del ${ns2} ip netns del ${nsrouter} @@ -332,6 +336,55 @@ EOF echo "PASS: tcp via loopback and re-queueing" } +test_icmp_vrf() { + ip -net $ns1 link add tvrf type vrf table 9876 + if [ $? -ne 0 ];then + echo "SKIP: Could not add vrf device" + return + fi + + ip -net $ns1 li set eth0 master tvrf + ip -net $ns1 li set tvrf up + + ip -net $ns1 route add 10.0.2.0/24 via 10.0.1.1 dev eth0 table 9876 +ip netns exec ${ns1} nft -f /dev/stdin <<EOF +flush ruleset +table inet filter { + chain output { + type filter hook output priority 0; policy accept; + meta oifname "tvrf" icmp type echo-request counter queue num 1 + meta oifname "eth0" icmp type echo-request counter queue num 1 + } + chain post { + type filter hook postrouting priority 0; policy accept; + meta oifname "tvrf" icmp type echo-request counter queue num 1 + meta oifname "eth0" icmp type echo-request counter queue num 1 + } +} +EOF + ip netns exec ${ns1} ./nf-queue -q 1 -t $timeout & + local nfqpid=$! + + sleep 1 + ip netns exec ${ns1} ip vrf exec tvrf ping -c 1 10.0.2.99 > /dev/null + + for n in output post; do + for d in tvrf eth0; do + ip netns exec ${ns1} nft list chain inet filter $n | grep -q "oifname \"$d\" icmp type echo-request counter packets 1" + if [ $? -ne 0 ] ; then + echo "FAIL: chain $n: icmp packet counter mismatch for device $d" 1>&2 + ip netns exec ${ns1} nft list ruleset + ret=1 + return + fi + done + done + + wait $nfqpid + [ $? -eq 0 ] && echo "PASS: icmp+nfqueue via vrf" + wait 2>/dev/null +} + ip netns exec ${nsrouter} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null @@ -372,5 +425,6 @@ test_queue 20 test_tcp_forward test_tcp_localhost test_tcp_localhost_requeue +test_icmp_vrf exit $ret diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json index 503982b8f295..91832400ddbd 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json @@ -68,7 +68,7 @@ "cmdUnderTest": "$TC action add action bpf object-file $EBPFDIR/action.o section action-ok index 667", "expExitCode": "0", "verifyCmd": "$TC action get action bpf index 667", - "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ok\\] id [0-9]* tag [0-9a-f]{16}( jited)? default-action pipe.*index 667 ref", + "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ok\\] id [0-9].* tag [0-9a-f]{16}( jited)? default-action pipe.*index 667 ref", "matchCount": "1", "teardown": [ "$TC action flush action bpf" diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json index 88a20c781e49..c6046096d9db 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json @@ -15,7 +15,7 @@ "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq", "expExitCode": "0", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]", "matchCount": "4", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" @@ -37,7 +37,7 @@ "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq", "expExitCode": "0", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-9,a-f][0-9,a-f]{0,2} bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-9,a-f][0-9,a-f]{0,2}", "matchCount": "256", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" @@ -60,7 +60,7 @@ "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq", "expExitCode": "2", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]", "matchCount": "4", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" @@ -82,7 +82,7 @@ "cmdUnderTest": "$TC qdisc del dev $ETH root handle 1: mq", "expExitCode": "2", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]", "matchCount": "0", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" @@ -106,7 +106,7 @@ "cmdUnderTest": "$TC qdisc del dev $ETH root handle 1: mq", "expExitCode": "2", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]", "matchCount": "0", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" @@ -128,7 +128,7 @@ "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq", "expExitCode": "2", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]", "matchCount": "0", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" |